ECCV2026 Segmentation AI paper notes paper summaries Adversarial Robustness Few-/Zero-Shot Learning Alignment/RLHF Object Detection Diffusion Models

✂️ Segmentation¶

🎞️ ECCV2026 · 94 paper notes

📌 Same area in other venues: 📷 CVPR2026 (122) · 🔬 ICLR2026 (31) · 🧪 ICML2026 (14) · 🤖 AAAI2026 (29) · 🧠 NeurIPS2025 (45) · 📹 ICCV2025 (73)

🔥 Top topics: Segmentation ×50 · Adversarial Robustness ×10 · Few-/Zero-Shot Learning ×8 · Alignment/RLHF ×6 · Object Detection ×5

LlamaSeg: Image Segmentation via Autoregressive Mask Generation: LlamaSeg uses a frozen VQGAN to turn masks into discrete visual tokens and a LLaMA-style model to generate them from images and text, reaching 55.9 mIoU on ADE20K at 384 pixels, while still trailing specialized discriminative methods in referring segmentation accuracy and latency.
Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation: DDAVS disentangles multi-source audio semantics using learnable queries anchored by a prototype memory bank, and introduces delayed bidirectional cross-attention in deep layers to align audio-visual modalities, comprehensively outperforming previous state-of-the-art (SOTA) methods on AVSBench and VPO multi-source/multi-category/multi-instance scenarios.
EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation: EM3M establishes a materials microstructure benchmark with 5,091 real electron micrographs, 2,985,660 instance annotations, and nine-dimensional structured descriptions, while SDXL augmentation and the adapted flow-based UniAIMS baseline raise full-dataset [email protected] from 0.800 with real-data training to 0.809 with mixed training.
Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation: HVLFormer converts pretrained vision-language class semantics into dataset- and image-aware multi-scale textual queries, then stabilizes mask decoding through layer-wise cross-view consistency, reaching 89.1% and 58.8% mIoU with 92 VOC labels and 232 COCO labels, respectively, using SigLIP2.
Beyond Aesthetics: Quantifying Information Loss in Turbid Scenes: The paper introduces the controlled TUB dataset and Phase-Congruency Delentropy (PCD) to distinguish unattractive underwater images from images that have lost task-relevant structure; PCD correlates most strongly with segmentation performance in the reported real and synthetic experiments, but is not a universal measure of recognizability across arbitrary scenes.
DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation: DGSeg has the MLLM emit two complementary cues — a textual semantic description of what the target is and a bounding-box spatial localization of where it is — routes them through two separate segmentation branches, and uses a lightweight dynamic gating module to estimate pixel-wise fusion weights, reaching 69.6 (val) / 67.3 (test) gIoU on ReasonSeg under the zero-shot setting and surpassing strong baselines such as Seg-Zero, CoPRS and SAM-Veteran.
ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis: ET-SAM employs a lightweight Point Decoder to predict word-level heatmaps for extracting sparse foreground points, replacing the convention in Hi-SAM of randomly sampling thousands of points from pixel-level segmentations. Coupled with learnable task prompts and a joint training strategy to utilize multi-granularity heterogeneous annotation data, it achieves competitive performance on HierText with approximately 3\(\times\) inference speedup, and improves the average F-score by 11.0% on Total-Text/CTW1500/ICDAR2015.
Fast and Flexible Robustness Certificates for Semantic Segmentation: This paper reduces certified robustness for semantic segmentation to "one forward pass plus one sort": a Lipschitz-constrained network yields per-pixel invariance radii, and "how many pixels can an attacker flip" is recast as a one-dimensional knapsack with capacity \((L\epsilon)^2\), delivering deterministic worst-case lower bounds on pixel accuracy, FNR, stability and class IoU for 1024×1024 Cityscapes images in about 0.1 s — roughly 600× faster than randomized smoothing.
MobileManiBench: Simplifying Model Verification for Mobile Manipulation: This paper proposes MobileManiBench, a large-scale mobile manipulation simulation benchmark based on Isaac Sim. By training reinforcement learning policies, it automatically generates 300K diverse manipulation trajectories (containing language instructions, multi-view RGB-D images, object/robot states, and actions) across 2 robot platforms, 630 objects, 5 skills, and 100 scenes. Multiple VLA models are systematically evaluated on this benchmark, providing a standardized platform for verifying VLA architectures in mobile manipulation tasks.
PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation: PanoSAM2 addresses projection distortion, left-right seams, and sparse object memory in panoramic videos through SAM2 decoder and memory adaptations plus geometry-aware supervision, raising Hiera-S from 60.2 to 65.8 \(\mathcal{J}\&\mathcal{F}\) on the 360VOTS test set at the cost of some inference speed.
StAR: Segment Anything Reasoner: Rather than proposing a new architecture, StAR dismantles the bottlenecks that suppress a base model's reasoning ability in an existing RLVR framework (VisionReasoner) along four axes—parameter-tuning scheme, reward design, learning strategy, and answer format—and is the first to bring parallel test-time scaling (mask-level majority voting) to segmentation; with only 5k training samples it lifts Qwen2.5-VL 7B on the ReasonSeg-X test set from 42.2 to 49.2 gIoU (50.3 with majority voting), while also contributing a cleaner ReasonSeg-R and a harder ReasonSeg-X benchmark.
Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching: By recombining intermediate features from frozen DINOv3, enhancing support representations with reliable query regions, and fusing prototype matching at multiple granularities, this method achieves average 1-shot / 5-shot mIoU of 68.39 / 73.08 across four target domains without task-specific training or target-domain fine-tuning.
UnderOneFacade: Worldwide Facade Semantic Segmentation Benchmark Dataset: UnderOneFacade collects centimeter-accurate facade point clouds of roughly 366 buildings in the UK (Nottingham), Germany (Munich), and Singapore using static terrestrial, backpack, and vehicle-mounted laser scanning, totaling 2.7B annotated points; it extends ZAHA's hierarchical Level-of-Facade-Granularity (LoFG) taxonomy (15 classes at LoFG3 / 5 at LoFG2) across countries with about 5,500 hours of manual annotation, and benchmarks six representative point cloud networks under a unified xyz-only, 100-epoch protocol, showing that the best model reaches only about 33 mIoU on fine-grained LoFG3 and that zero-shot cross-continental transfer roughly halves it again.
AFFMAE: Scalable Vision Pre-Training for High-Resolution Microscopy Segmentation on Desktop Hardware: AFFMAE integrates the adaptive off-grid token merging mechanism of AutoFocusFormer into the MAE framework. While maintaining an efficient asymmetric design that encodes only visible tokens, it enables mask-friendly pre-training of hierarchical backbones. This allows high-resolution microscopy image segmentation pre-training to be completed on a single consumer-grade GPU, matching the segmentation accuracy of ViT-MAE with equivalent parameters, while achieving a 2x increase in pre-training throughput and up to a 5x increase in high-resolution fine-tuning throughput.
Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs: FGOS-Net separates low-frequency topology modeling from high-frequency detail filtering, using deterministic sub-band-matched scanning and topology-conditioned active probes to reduce crack fragmentation and texture false positives; it achieves 91.29% mIoU and 97.12% clDice on DeepCrack, with 80.2 FPS under the paper's specified RTX 3090 evaluation setting.
DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation: DINOde introduces an ordinary differential equation (ODE)-based continuous cross-modal alignment framework that smoothly maps frozen CLIP text embeddings onto the self-supervised DINOv3 visual manifold via Semantic Text Flow, Global Context Flow, and Velocity Tangent Projection, achieving state-of-the-art results across 8 open-vocabulary benchmarks after just 4 hours of training on COCO Captions.
Editing Everything Everywhere All at Once: To tackle severe attribute leakage and harsh boundary stitching in multi-instruction concurrent image editing, MICE introduces a training-free, architecture-agnostic continuous attention biasing scheme that achieves strict attribute binding and natural visual harmonization in a single forward pass.
Evidence-Backed Video Question Answering: Addressing the black-box nature of current Video LLMs, this work introduces Evidence-Backed Video Question Answering (E-VQA), a task requiring models to jointly output semantic answers, temporal segments, and 6 FPS dense tracked segmentation masklets, accompanied by the human-verified ST-Evidence benchmark and a 160k instruction dataset ST-Evidence-Instruct.
Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting: The paper introduces Exclusion-Constrained Dual-Prompt SAM (EDP-SAM) with Nearest Neighbor Exclusion Circle (NNEC) priors to create benchmark mask annotations from point labels, paired with an Exclusivity-Guided Mask Learning (XMask) framework and pseudo-mask constraints that bridge dense crowd instance segmentation and crowd counting in a unified semi-supervised pipeline.
FeVOS: Foresight Expression Video Object Segmentation: Proposes the FeVOS (Foresight Expression Video Object Segmentation) task, which requires predicting future events and segmenting related objects based on visual cues in observed frames. It introduces a dataset containing 968 videos and 14,525 predictive expressions, accompanied by 2,904 synthetic Chain-of-Thought (CoT) annotations. A two-stage training framework, FeVOS-R1, is designed (CoT supervised fine-tuning cold start + GRPO reinforcement learning with pure IoU rewards for refined reasoning), achieving 42.3 J&F on FeVOS—a 6.5-point improvement over the fine-tuned Sa2VA baseline—while demonstrating strong zero-shot generalization capabilities on ReVOS (60.3) and MeViS (49.5).
FoundYou: A Unified Model for Personalized Segmentation and Retrieval: FoundYou repurposes the memory attention mechanism of a frozen SAM 2 for instance alignment across independent images, achieving a unified 52M-parameter personalized segmentation and retrieval model with only 5.9M trainable parameters running at 90 FPS (over 75x faster than PDM) while outperforming prior unified and task-specific baselines by +18.4 mIoU on PerMIS and +17.8 mAP on ILIAS.
Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection: Addressing the failure of diffusion models in Cross-Domain Few-Shot Object Detection (CDFSOD) caused by severe domain shifts, this paper decouples domain gaps into visual and semantic gaps, introducing a training-free framework termed Selective Inpainting with Tailored Noise (SITN) that achieves new state-of-the-art results across 6 CDFSOD and 4 CDFSS benchmarks.
GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks: Addressing the failure of existing slice discovery methods to capture contextual and relational instance-level errors, GH-ESD formulates error slice identification as grounded natural-language hypothesis generation coupled with monotonic sensitivity statistical verification, improving Precision@10 by 0.10 on the new GESD benchmark.
GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis: GroundingAnomaly introduces a few-shot anomaly image generation framework based on a pretrained diffusion model, fusing dense semantic maps with disentangled tokens via a Spatial Conditioning Module and injecting them into a frozen U-Net through gated self-attention layers to achieve spatially accurate, photorealistic defect synthesis.
HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy: To prevent coarse imaging modalities from suppressing fine-grained morphological hierarchies in single-cell self-supervised learning, HASSL introduces a double-teacher distillation framework guided by segmentation weak priors and a stability-weighted HDBSCAN hierarchical contrastive loss, achieving robust cross-modality alignment and morphology-driven subcluster separation across 2.3 million cells.
Hierarchical Prompt Injector for Domain Generalization Segmentation: Addressing diffuse attention and negative transfer caused by holistic category-level prompts and uniform injection in domain generalized semantic segmentation, this paper proposes Spatial Hierarchical Prompts (SHP) and the Hierarchical Prompt Injector (HPI) with dual-confidence gating and alignment losses, achieving state-of-the-art synthetic-to-real performance of 70.62% mIoU.
Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation: This paper proposes DHANet, which mitigates semantic over-alignment via hierarchical aggregation along the spatial dimension, and alleviates attribute over-alignment via hierarchical aggregation along the channel dimension. Supported by an online probabilistic semantic bank that offers auxiliary support information during inference, the proposed method achieves SOTA performance on four cross-domain few-shot segmentation benchmarks.
Hyperbolic Hierarchical Clustering for Visual Representation Learning: Addressing the black-box nature of conventional vision backbones and the quadratic complexity and Euclidean metric distortions of prior clustering backbones, this paper introduces an interpretable clustering token mixer (ClusterMixer) and the HCFormer architecture, which decouples local Euclidean patch clustering from global hyperbolic window clustering to achieve linear computational complexity, high accuracy, and strong interpretability.
Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment: The paper proposes GACR, an interpretation-oriented cloud removal framework that formulates recovery as an observation-anchored residual flow matching process coupled with a vision foundation model semantic manifold constraint, mitigating hallucinated artifacts and semantic drift while drastically improving downstream interpretation accuracy.
Layering Virtual Try-On: Addressing the core limitation where conventional virtual try-on models erase existing outfits via cloth-agnostic masks, this paper disentangles general VTON priors from specific layering logic through a two-stage mask-free training paradigm, achieving realistic clothing addition and de-layering while faithfully preserving inner-layer garments.
Learning Accurate Segmentation Purely from Self-Supervision: Selfment introduces a fully self-supervised foreground segmentation framework that operates without manual labels, pretrained segmentation priors (e.g., SAM), or CRF/bilateral post-processing: it generates an initial coarse partition via Normalized Cut on patch affinity graphs, refines it via Iterative Patch Optimization (IPO) in feature space, and trains a lightweight projection head with contrastive and region-consistency objectives to achieve new state-of-the-art results across salient and camouflaged object detection benchmarks.
Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation: Addressing the lack of semantic structure in traditional morphological noise for mask refinement, Phoenix introduces embedding-space adversarial perturbation to generate realistic, controllable noise patterns and pairs it with Tri-directional Contrastive Mask Refinement Learning (CMRL), achieving state-of-the-art performance across weakly-supervised, instance, and fine-grained segmentation tasks.
Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation: To tackle high measurement sparsity, multi-path return fragmentation, and inter-view measurement density imbalance in multi-view radar semantic segmentation, HyperRadar introduces learnable hypergraph reasoning to capture higher-order dependencies among grouped returns and leverages Unbalanced Optimal Transport (UOT) for mass-relaxed, correspondence-free cross-view feature alignment, establishing new state-of-the-art benchmarks on CARRADA (63.8% mIoU) and RADIal (83.4% mIoU).
Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks: Addressing the fragmentation where conventional surrogate-based black-box transfer attacks optimize initialization, perturbation crafting, and model adaptation in isolation, this paper presents BMAT (Bilevel-Minimax Adversarial Transfer), unifying all three into a principled bilevel-minimax optimization problem solved via a Soft Weight Modulator and an Implicit Gradient Approximator, substantially boosting cross-architecture transferability on classification and semantic segmentation benchmarks.
Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection: Addressing the architectural spectral bias of single-paradigm backbones in general salient object detection, LFNet treats continuous global semantics from VMamba and fine-grained local textures from ConvNeXt as evolving states and exogenous stimuli within a continuous liquid dynamic system, achieving state-of-the-art performance across RGB, RGB-D, RGB-T, VSOD, and VDT tasks with superior parameter efficiency.
LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models: To tackle topological collapse and effective receptive field reconvergence caused by naive 4D kernel flattening in LoRA, LoCA introduces a spatial-channel decoupled convolutional adaptation framework combining low-rank channel mixing, covariance SVD spatial basis refinement, and hierarchical rank scheduling, significantly outperforming full fine-tuning and prior PEFT baselines on domain-generalized segmentation and visual adaptation.
ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation: ModuSeg explicitly decouples weakly supervised semantic segmentation into two independent phases: "class-agnostic object discovery" and "semantic retrieval." It extracts geometric proposals using a generic Mask Proposer and performs non-parametric retrieval using an offline-constructed feature bank. Without any fine-tuning, the method achieves state-of-the-art performance on the Pascal VOC dataset with 86.3 mIoU using only image-level labels during training.
Pixel-wise Planarity for High-Precision Monocular Plane Segmentation: This paper presents a high-precision monocular plane segmentation framework that freezes a pretrained monocular geometric backbone, attaches a lightweight pixel-wise planarity prediction head, and performs GPU-parallel non-iterative region growing alongside geometry-consistent ground truth generation, dramatically suppressing false planar detections under strict distance thresholds.
RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation: Addressing frequent noise, blur, and sensor distortion in visible and thermal modalities, RA-SOD models modality reliability across encoding, decoding, and fusion stages using residual MoE feature modulation, uncertainty-guided dual-stream bidirectional correction, and pixel-wise modality competition, achieving state-of-the-art robustness in degraded environments.
Residual-Guided Expert Specialization for Incomplete Multimodal Learning: MARS proposes a Mixture-of-Experts (MoE) framework that captures the representation shift patterns caused by missing modalities by computing the residual between full and incomplete modality representations to guide expert specialization. Concurrently, it introduces dual-router distillation and discrepancy-aware noise regularization to tackle training-inference routing inconsistency, comprehensively outperforming state-of-the-art (SOTA) methods on four incomplete multimodal classification and segmentation datasets.
SAM-MT: Real-Time Interactive Multi-Target Video Segmentation: Built upon the SAM2 framework, SAM-MT transforms multi-target video segmentation into an efficient interactive system by combining decoupled masked attention with a query-based sparse memory, completely decoupling inference latency from target count to achieve over 36 FPS in real-time across 10+ targets.
SARIF: Segment Anything for Robust Image Forensics: SARIF simultaneously runs a frozen original SAM encoder and a LoRA fine-tuned encoder, calculating the residuals between them at each global attention layer as forgery-specific cues. These are then fused with the predicted mask from the previous round into prompts, driving SAM's original lightweight decoder to perform 5-step progressive refinement, achieving the strongest average performance in cross-dataset forgery localization.
Seek to Segment: Active Perception for Panoramic Referring Segmentation: Addressing the bottleneck of static referring image segmentation, this paper proposes the Active Panoramic Referring Segmentation (APRS) task along with PanoSeeker—an embodied agent utilizing explicit spherical visual memory (EgoSphere) and GRPO reinforcement learning to achieve efficient non-redundant search and accurate target alignment.
Segmentation-Guided Homography Estimation for Long-Term Planar Tracking: This paper introduces SAM-H, a training-free geometric pipeline that extracts 8-DoF homographies from SAM 2 segmentation masks via Hough line intersections and DINOv2 symmetry disambiguation, and combines it with optical flow into WOFTSAM to achieve state-of-the-art performance on PlanarTrack and POT-210.
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing: SegFS proposes a dual-path fast-and-slow framework for open-vocabulary video instance segmentation (OV-VIS). It runs a full object-centric model on sparse keyframes to extract instance embeddings, and then projects these embeddings back into the backbone feature space. A lightweight Fast Feature Aggregator is utilized on intermediate frames to complete efficient instance relocation and segmentation. This approach achieves up to a 14x reduction in on-device latency and crosses the 30 FPS real-time threshold on mobile devices for the first time, while limiting the performance drop to within 1 AP.
SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation: Addressing the immense search space and misleading step-transition rewards in decision-based black-box sparse attacks on semantic segmentation, SegPAR introduces a class-centric exploration framework coupled with a discrepancy reward that penalizes misclassification reversion, achieving unprecedented MIoU degradation under extreme pixel sparsity.
Semantic Generative Tuning for Unified Multimodal Models: This paper introduces Semantic Generative Tuning (SGT), a novel post-training paradigm that adopts image segmentation as a high-level generative proxy to bridge the representation gap between visual understanding and generation in unified multimodal models, achieving mutual reinforcement across perception and synthesis benchmarks.
STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation: STARLINC tackles the surging crisis of low Earth orbit satellite trail contamination in astronomical surveys by leveraging temporal redundancy across repeated exposures to construct SSIM-based differential maps and pairing them with classifier Grad-CAM heatmaps, training a U-Net on synthetic trails to achieve 0.485 mIoU pixel-level masking without requiring any manual pixel-level annotations on real astronomical images.
Toward Robust In-Context Segmentation via Concept Guidance: CG-ICS reformulates the in-context segmentation problem as a concept-guided prompt segmentation problem: an MLLM is employed to generate candidate concepts, which are then scored by SAM3 and selected via tree search to find the optimal textual concept. Concurrently, an image-stitching technique extracts query-side visual exemplars from the reference images. Both cues jointly drive a frozen SAM3 to complete the segmentation, which significantly reduces performance variance caused by reference selection while maintaining high accuracy.
Unified Video Dense Prediction from Disjoint Data: To tackle the fragmentation of dense prediction datasets across incompatible domains and the acute scarcity of multi-task video annotations, UniD leverages pretrained diffusion visual priors to train per-task specialists on disjoint datasets, distilling them into a unified video backbone via lightweight latent projectors in a single forward pass without co-annotation or pseudo-labeling.
Unsupervised Semantic Segmentation Facilitates Model Understanding: Addressing the lack of intuitive visualization tools for internal representations in self-supervised Vision Transformers, this work establishes an unsupervised semantic segmentation and mutual-information probing protocol, revealing that dominant positional effects in Key/Query embeddings trigger downstream locality bias in Masked Image Modeling and identifying severe spatial boundary artifacts as a key driver of inverse scaling in DINOv3-Large.
VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection: Addressing the multi-modality representation homogenization caused by uniform ground-truth mask supervision in RGB-D camouflaged object detection, this paper proposes VCP-DCN, a progressive depth collaborative network that decouples, aligns, interacts, and adaptively fuses modality-consistent and modality-specific prototype representations, achieving state-of-the-art performance across CAMO, COD10K, and NC4K benchmarks.
When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization: To fix the catastrophic failure of Transformer-based camouflaged object detection under post-training W4A4 quantization—where heavy-tailed background tokens inflate shared clipping ranges and push subtle boundary cues into the zero bin—COD-TDQ couples Direct-Sum Token-Group scaling (DSTG) with Dual-Constraint Range Projection (DCRP) to restore accuracy and enable a 1.50x real inference speedup without retraining.
Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence: Discovering that contrastive audio-visual learning naturally exhibits selective convergence towards dominant sound sources in mixtures, this paper proposes SCAV, an annotation-free two-stage progressive decoupling framework, and introduces the large-scale pixel-level VGGSound-DuetMask benchmark.
X2SAM: Any Segmentation in Images and Videos: X2SAM uses Qwen3-VL as the reasoning core and the SAM2 mask encoder for fine-grained features, adding a language-conditioned Mask Memory to extend image-style any-segmentation to video; one conversational interface covers 14 image and video segmentation tasks under both textual and visual prompts, achieving 69.9 J&F on ReVOS video reasoning segmentation, 75.8 mIoU on video GCG, and cutting joint-training cost by about 36.5%.
ZMIS-SAM: Segment Anything Model Enhanced With Wavelet Transform For Zooplankton Microscopy Image Instance Segmentation: ZMIS-SAM adapts SAM's ViT-H image encoder with shape/intensity adapters (ZM-ViT), general/domain-specific feature aggregation (NFAM), and multi-scale, multi-directional wavelet enhancement (WM2FE), alongside the first dataset introduced for this task, ZMIS5K (5,358 pixel-annotated images, 47 species, and 10,228 instances), achieving 73.6 mAP / 94.6 AP50 / 80.7 AP75 on its test set—gains of 1.8 / 2.4 / 3.8 points over the strongest SAM-based baseline, RSPrompter.
CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Image Segmentation: Targeting high-frequency energy decay and excessive boundary smoothing caused by global normalized aggregation in Visual State Space Duality (VSSD), CRISP introduces a linear-complexity Duality Calibration Operator (DCO) that reuses aggregation statistics alongside an end-to-end Orthogonal Multi-Prototype (OMP) decoder, effectively preserving fine-grained multi-modal features and crisp boundaries with only ~32M parameters.
CURE: Contextual Debiasing and Unbiased Refinement for Training-Free Open-Vocabulary Semantic Segmentation: To tackle global contextual bias and feature homogenization in training-free open-vocabulary semantic segmentation using vision-language models, CURE introduces a training-free three-stage framework that eliminates explicit high-norm outlier tokens via local neighborhood reconstruction, removes implicit shared global bias through non-outlier feature centroid subtraction, and refines spatial coherence using mid-level correlation priors.
Deformable and Multi-view Gradient-Aligned Physical Adversarial Camouflage: Addressing spatial gradient discontinuity and destructive cross-view gradient conflicts in 3D physical adversarial camouflage, this paper proposes a continuous Deformable Texture Field (DTF) decoupling appearance from geometric deformation, coupled with a Gradient-Aligned Meta-Optimization (GAMO) strategy that implicitly maximizes cross-view gradient alignment via multi-step exploration trajectories to achieve robust, perspective-invariant vehicle evasion.
DocLayout-VL: A Foundational Model for Hierarchical, Open-set, and Promptable Document Layout Segmentation: DocLayout-VL reframes document layout understanding as promptable open-set hierarchical segmentation, unifying serialized tree parsing in a VLM backbone, structural context modeling via a Hierarchical Grounding Contextualizer (HGC), and pixel-accurate SAM mask decoding to achieve new state-of-the-art results across 14 layout benchmarks.
E-MOTION: A Dataset for Event-Based Scene Flow Estimation with Independent Moving Objects: E-MOTION is the first large-scale benchmark dataset captured with real high-resolution stereo event cameras, delivering 200 Hz sub-millimeter dense 3D scene flow, depth, optical flow, and instance segmentation ground truth in scenes featuring independent moving objects and complex handheld motions.
EDM:Event-guided Diffusion Model for Video Shadow Detection in Complex Dynamic Scenes: The first work introducing event cameras into video shadow detection, proposing an Event-guided Diffusion Model (EDM) with motion trajectory attention and bidirectional mask generation, alongside a new real-world benchmark EVSD to conquer severe motion blur and extreme illumination changes.
Forget, Anticipate and Adapt: Test Time Training for Long Videos: This paper proposes the Frame Forgetting Network (FFN). By adopting a "forget-anticipate-adapt" mechanism that processes only the leaving and entering frames of a sliding window, FFN reduces the computational complexity of test-time training (TTT) for long videos from \(O(k)\) to a constant \(O(1)\). Moreover, it dynamically determines when to execute TTT based on a "surprise" metric, achieving a superior accuracy-efficiency trade-off across dense segmentation, depth estimation, and action classification.
Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent: To tackle the challenge of selecting suitable remote sensing foundation models under heterogeneous documentation and strict deployment constraints, this paper introduces RS-FMD (a structured database of 160+ RSFMs) and Remsa, a constraint-aware LLM agent that automates transparent model selection via structured metadata grounding, adaptive orchestration, and in-context ranking.
Free‑CD: Probabilistically Decoupled Training-Free Open-Vocabulary Change Detection with Resolution-Invariant Feature Inversion: Free-CD addresses the over-segmentation and boundary ambiguity caused by instance proposal networks in traditional open-vocabulary change detection by decoupling change detection into potential change probability estimation and bi-temporal open-vocabulary segmentation without task-specific training, setting new state-of-the-art benchmarks via resolution-invariant feature upsampling (RIFI-Up) and Bayesian probability correction.
Frequency Director: Learnable Mixture of Frequency Experts for Unified Concealed Scene Segmentation: To resolve the large distribution discrepancies across heterogeneous imaging modalities and the intrinsic difficulty of subtle targets in unified concealed scene segmentation, this paper proposes FreqDirect, a lightweight and prompt-free framework that dynamically modulates task-specific frequency bases via a Mixture of Frequency Experts (MoFE) while preserving structural topology via a Spatial Commonality Anchor (SCA), tuning only ~5% parameters to outperform existing unified models and rival specialist models across eight scenarios.
From Script to Shot: A Benchmark for Grounding Screenplays in Movies: Introduces "From Script to Shot", the first benchmark spanning 50 feature films over nine decades with 55K+ human-verified scene-to-shot alignments, uncovering the dialogue anchoring effect in multimodal grounding and demonstrating strong downstream utility in zero-shot scene segmentation and guided text-to-video generation.
From Visual Primitives to Semantic Masks: Fine-Grained Visual-Linguistic Alignment for Open-Vocabulary Remote Sensing Image Segmentation: Addressing visual self-similarity and text representation collapse in fine-grained remote sensing scenes, SANO3 introduces a training-free framework that extracts visual primitives from DINOv2 self-similarity priors, aligns them via Plackett-Luce ranking structure matching, injects hybrid prototypes into the text stream, and greedily selects positive/negative point prompts via entropy reduction, achieving state-of-the-art performance on the newly constructed FG-OVSSRS Bench.
Geo-DPO: Aligning Semantic Intent with Geometry for 3D Affordance Segmentation: Addressing the severe geometric ambiguity and boundary overflow caused by the over-compression of the <SEG> token in 3D MLLM sequential affordance segmentation, Geo-DPO introduces a Hierarchical Geometry Adapter to inject multi-scale physical features into the semantic query and Contrastive Affordance Preference Optimization to penalize mask overflow via hybrid position and shape prototype rewards.
Harnessing SSL for Segmentation in 3D Microscopy with Noisy Labels and Hard Patches: To tackle label scarcity, semi-automated label noise, and imaging artifacts in 3D microscopy, this paper presents \(\mu\text{3DINO}\), a foundation 3D ViT pretrained on over 2 million volumes, and \(\mu\text{DivSeg}\), a dual-model co-training pipeline that uses feature queues to decouple patch noise from hardness, achieving state-of-the-art segmentation and self-correction beyond silver ground truth.
HIDA: A Human-Intuition-Guided Depth-Aware Framework for Zero-Shot Amodal Segmentation: HIDA integrates frozen SAM and Depth Anything V2 as plug-and-play prior generators, leveraging depth-polarity adaptive cropping to focus on occluded regions and an occlusion-aware token-routing soft MoE to empower a lightweight ViT, achieving state-of-the-art zero-shot and fully supervised amodal segmentation using only visible bounding boxes.
IACD: Iterative Adversarial Collaborative Detection via Dual-Perspective Blind Spot Discovery: To overcome the systematic false negatives of appearance-only detectors on concealed targets, IACD introduces a Seeker-Hider collaborative framework that keeps a pretrained YOLOv11m frozen while training a lightweight ~9M parameter Hider solely on detector false negatives to locate blind spots and guide a second detection pass via bounded residual attention gates.
Intra-Class Consistency Guided Class-Agnostic Event Segmentation: To tackle weak intra-class consistency caused by the spatial sparsity of event data, IC2-ESeg explicitly recovers noise, motion, and brightness representations in a learning-free, physics-grounded manner, injecting them into an image encoder via staged adapters and transferring SAM's open-world segmentation capability via cross-modal distillation.
Iterative Refinement of Semantic and Spatial Representations for Open-Vocabulary Camouflaged Object Segmentation: Addressing error accumulation from unidirectional one-shot semantic injection in open-vocabulary camouflaged object segmentation, ISSR establishes a closed-loop bidirectional interaction between a spatial-structure-aware category re-ranker and a semantic-context modulator, iteratively refining masks and category representations to boost cSm by 14.4% on OVCamo.
Kiroshi: An Agentic Perception System for High-Accuracy Image Parsing: Addressing the reliance of interactive matting on tedious manual verification and the inability of multimodal large language models (MLLMs) to capture pixel-level fine boundaries, Kiroshi reformulates image parsing into an explicit plan-and-act agentic loop where an MLLM emits compact text-based grid actions to steer an attention-guided action model, aligned via residual-sampled trajectory Direct Preference Optimization (DPO) for fully automated, high-fidelity matting and segmentation.
LogFA: Efficient Feature-Space Data Augmentation for Egocentric Temporal Action Segmentation: LogFA introduces a highly efficient feature-space data augmentation framework for egocentric temporal action segmentation, combining prompt-enhanced cross-modal textual features for intra-action variations with a Generalized DAG for inter-action sequence diversification without pixel synthesis.
MiNQVIS: Mitigating Noisy Queries for Robust Online Video Instance Segmentation: Targeting the corruption of temporal association and contrastive supervision caused by noisy queries under heavy occlusion, blur, and clutter, MiNQVIS introduces query-level gating, video-level prototypical contrastive learning, and dual-memory fusion to achieve robust, drift-resistant online video instance segmentation.
MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation: MomentSeg presents a unified framework that co-optimizes Temporal Sentence Grounding (TSG) and Referring Video Object Segmentation (RefVOS) through a native [FIND] token matching mechanism, a density-modulated Moment-Centric Sampling (MCS) strategy, and Bidirectional Anchor-updated Propagation (BAP), outperforming existing models by 5% on MeViS and 6% on ReVOS without relying on external keyframe models.
NAPA: Natively Multimodal Autoregressive Perception Architecture: Presents Falcon Perception (NAPA), a single early-fusion Transformer that eliminates the encoder-decoder split via a hybrid bidirectional-causal attention pattern and an autoregressive Chain-of-Perception interface, enabling high-resolution masks via parallel dot-product decoding.
NUN: Nested Unfolding Network for Real-World Concealed Object Segmentation: To resolve the fundamental optimization conflict between low-level texture restoration and high-level semantic segmentation in degraded real-world concealed object scenarios, NUN introduces the first DUN-in-DUN nested unfolding network, decoupling parameter spaces via bi-level proximal gradient optimization and controlled bi-directional interaction across 12 diverse benchmarks.
PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification: PhenoLeaf-TS presents the first large-scale time-series plant phenotyping benchmark spanning 21 Arabidopsis genotypes, 318 plant replicates, and 17,082 top-down RGB images with temporally consistent 31-colour-coded leaf instance masks, systematically evaluating 21 baseline models across segmentation, tracking, and growth classification while demonstrating up to +51 mAP cross-dataset transfer gains.
PoseImageNet: Pose Estimation for Extensive Classes Based on Rich Structure Prototypes: Addressing the long-standing restriction of pose estimation to single classes and rigid topologies, this work introduces PoseImageNet on ImageNet spanning 720 semantic classes and 3,500+ structure prototypes grounded on TPS deformation alignment, alongside a momentum cost-matched query decoder baseline achieving 57.0% [email protected] across extensive classes.
QST-SAM: Leveraging Cross-modal Instructions for Few-shot Referring Video Object Segmentation: Addressing cross-video textual semantic mismatch and multi-modal alignment challenges in Few-Shot Referring Video Object Segmentation (FSRVOS), this paper decouples semantic intent from visual exemplars (retaining language supervision exclusively at the query level) and introduces QST-SAM on top of SAM 2, integrating a Support Instruction Compressor, a tripartite Q-S-T Transformer, and a Multi-Priors Prompting module to achieve state-of-the-art segmentation.
ReliefSAM: A Geometry-Augmented Multi-Prior Adapter for Bas-Relief Segmentation: Addressing the severe lack of chromatic and geometric contrast in monocular bas-relief archival photographs, ReliefSAM freezes the SAM backbone and explicitly injects image-aligned depth and soft-edge priors via a lightweight multi-prior feature encoder and bidirectional interaction adapters, establishing accurate prompt-free human figure segmentation.
Rethinking Adversary in Semantic Segmentation: An Out-of-Distribution Perspective: Addressing the limitation that conventional prediction-driven segmentation adversaries only perturb features along the in-distribution (ID) manifold to cross decision boundaries, SegOOD proposes driving adversarial representations off the ID manifold via Feature Wasserstein Separation and Weighted KNN Separation, significantly enhancing adversarial training against both ID-style and OOD-like attacks.
Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision: MoSA introduces a three-stage unsupervised framework that extracts multi-granularity motion pseudo-labels from unlabeled videos, internalizes a static appearance-driven objectness prior via contrastive perceptual grouping, and adapts to whole-image and interactive segment-anything architectures without any manual annotations.
SGQA: Semantic-Geometric Quality Alignment for Training-Free Few-Shot Instance Segmentation: Addressing the quality disconnect between semantic matching and mask geometry in training-free foundation model composition, this paper employs progressive oracle replacement to trace 64% of the performance gap to the scoring stage, and proposes SGQA—a hyperparameter-free geometric mean fusion that unifies semantic and geometric scores, boosting performance significantly without fine-tuning.
SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy: SkelEM proposes a self-supervised axial super-resolution framework that completely decouples the training signals (no shared gradients) between a topological skeleton network and a diffusion refiner. By utilizing a frozen, deterministic skeleton to anchor the structural topology and using truncated diffusion to recover high-frequency biological textures in 5 steps or fewer, this method achieves the best balance between fidelity, perceptual quality, and inference speed among self-supervised methods, while reaching SOTA performance on downstream membrane segmentation tasks.
Steerable Visual Representations: SteerViT interleaves lightweight gated cross-attention layers inside a frozen ViT (such as DINOv2), enabling language to intervene during the visual encoding process. Trained via a patch-level referring segmentation proxy task, it adds only 21M parameters to allow natural language to "steer" visual features and focus on arbitrary objects. Meanwhile, it maintains the representation quality of the original ViT, achieving zero-shot parity with or outperforming specialized methods on text-conditioned retrieval, personalized object discrimination, and industrial anomaly segmentation tasks.
SyncVL: Synchronizing Vision ⟷ Language Using Unsupervised Adaptation: Addressing the modality gap and domain shift in contrastive vision-language models without target labels, SyncVL freezes pretrained backbones and introduces bidirectional lightweight Transformer synchronizers optimized through group relative policy optimization (GRPO) consistency and alignment rewards alongside latent mutual distillation.
Thermo-JEPA: Learning a Geometry-Grounded Thermal World Model via Cross-Modal Privileged Masking: Addressing intra-frame spatial homogenization caused by thermal equilibrium in infrared video, Thermo-JEPA introduces a privileged information learning paradigm that injects confidence-gated spatial topology from paired RGB frames into the EMA teacher's attention mechanism as a soft prior, preventing representation collapse and modal pollution while achieving state-of-the-art pure-thermal dynamics prediction.
Towards Unsupervised Multi-modal Semantic Segmentation: To tackle the severe fusion degradation where naive multi-modal extensions hurt unsupervised segmentation, UniM2 introduces Cross-modal Correspondence Synergy (CMCS) to discover shared semantic manifolds alongside an asymmetric Cross-modal Harmonizer (CMH) that buffers gradient contradictions, delivering substantial gains of +6.4% mIoU on NYU-Depth-v2 and +9.8% mIoU on MFNet.
When Specialists Meet Generalists: Segmenter-Coordinated Asymmetric Learning for Label-Deficient Concealed Object Segmentation: SCALER introduces a segmenter-coordinated asymmetric co-training framework that alternately optimizes a mean-teacher specialist segmenter and a learnable generalist foundation model (SAM/SAM2/SAM3) using distinct, bias-tailored objective functions, achieving consistent improvements across eight label-deficient concealed object segmentation tasks.
XSemanticFlow: Cross Object Semantic Alignment for Zero-shot Manipulation: XSemanticFlow predicts cross-instance soft correspondences on PartField feature fields with hierarchical self-/cross-attention that sees semantics only, never coordinates, trained in three stages — SE(3) backbone fine-tuning, self-supervised cross-pose alignment on Objaverse, and supervised fine-tuning on PartNet-Coseg; it improves self-segmentation by +19.1 mIoU / +20.6 accuracy and cross-instance cosegmentation by +10.9 mIoU / +12.5 accuracy over the strongest baseline, and its single-reference zero-shot remapping reaches 80% on Mug Hanging and 70% on Block Pouring, well above video-generation baselines.