This is a repository of the segmentation method and graph method. In the segmentation part, the instance, semantic, panoptic and referring segmentation are included. In the graph part, the representation learning, clustering and so on methods are included. We will update continue...

util 2025.03.05: include CVPR, ECCV, ICCV, AAAI, ACMMM, WACV, and arxiv. (2019-2025)

---

• Instance, Semantic and Panoptic Segmentation
• Graph Representation and Cluster
• Referring Segmentation

Instance, Semantic and Panoptic Segmentation

ICML2025	unMORE:Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning	code	√√√
ICML2025	Balanced Learning for Domain Adaptive Semantic Segmentation	None
ICML2025	Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation	None
ICML2025	LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation	None
ICML2025	Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation	None
ICML2025	EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation	code
ICML2025	Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation	code	√√√
ICML2025	Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation	None
ICML2025	EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation	code
CVPR2025	Segment Any-Quality Images with Generative Latent Space Enhancement	code
CVPR2025	LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation	code
CVPR2025	BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis	code
CVPR2025	Exploring CLIP’s Dense Knowledge for Weakly Supervised Semantic Segmentation	code	√√√
CVPR2025	SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories	code	√√√
CVPR2025	Rethinking Query-based Transformer for Continual Image Segmentation	code
CVPR2025	FSHNet: Fully Sparse Hybrid Network for 3D Object Detection	code
CVPR2025	One-for-More: Continual Diffusion Model for Anomaly Detection	code
CVPR2025	UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection	code
CVPR2025	Exploring CLIP’s Dense Knowledge for Weakly Supervised Semantic Segmentation	code
AAAI2025	MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation	code
AAAI2025	FOCUS: Towards Universal Foreground Segmentation	code	foreground seg., √√√
arxiv24.01	Bilateral Reference for High-Resolution Dichotomous Image Segmentation	code	√√√√
TMI2024	BoNuS: Boundary Mining for Nuclei Segmentation With Partial Point Labels	code	√√√√
ECCV2024	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance	code
SIGGRAPH2024	SAM 2: Segment Anything in Images and Videos	code	√√√
CVPR2023	Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation	code	√√√
ECCV2024	Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes	code	√√√
CVPR2024	Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation	code	√√√
ECCV2024	VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation	code	√√√
arxiv2024	Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation	code	√√√
ECCV2024	Semantic-aware SAM for Point-Prompted Instance Segmentation	code	√√√
ECCV2022	Point-to-Box Network for Accurate Object Detection via Single Point Supervision	code	√√√
ECCV2024	Semantic-SAM: Segment and Recognize Anything at Any Granularity	code	√√√
ECCV2024	Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively	code	√√√
arxiv2024	Segment Anything without Supervision	code	√√√
CVPR2024	Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion	code	√
CVPR2024	CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor	code	√√
CVPR2024	PEM: Prototype-based Efficient MaskFormer for Image Segmentation	code
CVPR2024	Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation	code
CVPR2024	Clustering Propagation for Universal Medical Image Segmentation	code	√
CVPR2024	Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation	code
CVPR2024	Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation	code
CVPR2024	Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentation	code
CVPR2024	Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation	code	√
CVPR2024	From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation]	code
CVPR2024	Frequency-Adaptive Dilated Convolution for Semantic Segmentation	code
CVPR2024	Tyche: Stochastic In-Context Learning for Medical Image Segmentation	code	√
CVPR2024	EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation	code	√
CVPR2024	ASAM: Boosting Segment Anything Model with Adversarial Tuning	code
CVPR2024	Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation	code
CVPR2024	Open-Vocabulary Semantic Segmentation with Image Embedding Balancing	code
CVPR2024	Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance	code
CVPR2024	Contextrast: Contextual Contrastive Learning for Semantic Segmentation	None
CVPR2024	Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation	None
CVPR2024	Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation	code	√√√
CVPR2024	ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers	code
CVPR2024	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation	None
CVPR2024	Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation	code
CVPR2024	ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting	code	√√√
CVPR2024	Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation	code	√√√
CVPR2024	Unsupervised Universal Image Segmentation	code	√√√
CVPR2024	Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models	code
CVPR2024	Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior	code
CVPR2024	Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors	code
CVPR2024	Mudslide: A Universal Nuclear Instance Segmentation Method	None	√
CVPR2024	Class Tokens Infusion for Weakly Supervised Semantic Segmentation	code
CVPR2024	Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling	code	√√√
CVPR2024	ToNNO: Tomographic Reconstruction of a Neural Network’s Output for Weakly Supervised Segmentation of 3D Medical Images	None
CVPR2024	Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation	code
CVPR2024	Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation	code
CVPR2024	EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation	code
CVPR2024	MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation	code
CVPR2024	Open-Vocabulary 3D Semantic Segmentation with Foundation Models	None
CVPR2024	AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation	code	√√√
CVPR2024	Collaborating Foundation Models for Domain Generalized Semantic Segmentation	code	√√√
CVPR2024	SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation	code
CVPR2024	Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation	code	√√√
CVPR2024	PSDPM: Prototype-based Secondary Discriminative Pixels Mining for Weakly Supervised Semantic Segmentation	code
CVPR2024	Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation	code
CVPR2024	USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation	None
CVPR2024	Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation	code
CVPR2024	Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation	code
CVPR2024	One-Prompt to Segment All Medical Images	code	√√√
CVPR2024	DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation	code
CVPR2024	RankMatch: Exploring the Better Consistency Regularization for Semi-supervised Semantic Segmentation	None
CVPR2024	Open-World Semantic Segmentation Including Class Similarity	code
CVPR2024	Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincar´e Ball	code
CVPR2024	Diversified and Personalized Multi-rater Medical Image Segmentation	code	√
CVPR2024	MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling	code
CVPR2024	Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation	code
CVPR2024	AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning	code
CVPR2024	UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes	code
CVPR2024	Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations	code
CVPR2024	Semantic-aware SAM for Point-Prompted Instance Segmentation	code
CVPR2024	RobustSAM: Segment Anything Robustly on Degraded Images	code	√
CVPR2024	SAI3D: Segment Any Instance in 3D Scenes	code
CVPR2024	CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation	code
CVPR2024	Open-Set Domain Adaptation for Semantic Segmentation	code	√
CVPR2024	BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance	code
CVPR2024	PH-Net: Semi-Supervised Breast Lesion Segmentation via Patch-wise Hardness	code	√√
CVPR2024	Extreme Point Supervised Instance Segmentation	code
CVPR2024	Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image Segmentation	code
CVPR2024	Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Multi-Scale Aggregation and Anthropic Prior Knowledge	code	√√
CVPR2024	EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything	code	√
CVPR2024	Open-Vocabulary Segmentation with Semantic-Assisted Calibration	code
CVPR2024	MFP: Making Full Use of Probability Maps for Interactive Image Segmentation	code
CVPR2024	GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation	code
CVPR2024	Guided Slot Attention for Unsupervised Video Object Segmentation	code
WACV2024	AnyStar: Domain randomized universal star-convex 3D instance segmentation	code	√√√
WACV2024	Revisiting Token Pruning for Object Detection and Instance Segmentation	code
WACV2024	BPKD: Boundary Privileged Knowledge Distillation for Semantic Segmentation	code
WACV2024	Guided Distillation for Semi-Supervised Instance Segmentation	code
ICCV2023	SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning	code
ICCV2023	SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning	code
ICCV2023	Exploring Transformers for Open-world Instance Segmentation	code
ICCV2023	Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision	code
ICCV2023	Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation	None
ICCV2023	Probabilistic Modeling of Inter- and Intra-observer Variability in Medical Image Segmentation	code	√√√
ICCV2023	Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation	code	√√
ICCV2023	MSI: Maximize Support-Set Information for Few-Shot Segmentation	code	√√
ICCV2023	TopoSeg: Topology-Aware Nuclear Instance Segmentation	code	√√√
ICCV2023	MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory	code
ICCV2023	Informative Data Mining for One-shot Cross-Domain Semantic Segmentation	code
ICCV2023	Segmenting Known Objects and Unseen Unknowns without Prior Knowledge	code
ICCV2023	RbA: Segmenting Unknown Regions Rejected by All	code	√
ICCV2023	Segment Anything	code
ICCV2023	SimpleClick: Interactive Image Segmentation with Simple Vision Transformers	code
ICCV2023	Texture Learning Domain Randomization for Domain Generalized Segmentation	code
ICCV2023	Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images	code	√√√
ICCV2023	XNet: Wavelet-Based Low and High Frequency Fusion Networks for Fully- and Semi-Supervised Semantic Segmentation of Biomedical Images	code	√√√
ICCV2023	CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation	code
ICCV2023	Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network	code
ICCV2023	BoxSnake: Polygonal Instance Segmentation with Box Supervision	code
ICCV2023	UniverSeg: Universal Medical Image Segmentation	code	√√√
ICCV2023	Enhancing Modality-Agnostic Representations via Meta-learning for Brain Tumor Segmentation	None	√√√
ICCV2023	CauSSL: Causality-inspired Semi-supervised Learning for Medical Image Segmentation	code
ICCV2023	MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation	code
ICCV2023	Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation	code
ICCV2023	Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation	code
ICCV2023	Global Knowledge Calibration for Fast Open-Vocabulary Segmentation	code
ICCV2023	Open-vocabulary Panoptic Segmentation with Embedding Modulation	code
ICCV2023	MasQCLIP for Open-Vocabulary Universal Image Segmentation	code
ICCV2023	WaterMask: Instance Segmentation for Underwater Imagery	code
ICCV2023	CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection	code	√√√
ICCV2023	SegGPT: Towards Segmenting Everything In Context	code
ICCV2023	Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning	code
ICCV2023	DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models	code	√
ICCV2023	Scratch Each Other’s Back: Incomplete Multi-modal Brain Tumor Segmentation Via Category Aware Group Self-Support Learning	code	√
ICCV2023	EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation	code
ICCV2023	Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only	code
ICCV2023	Pseudo-label Alignment for Semi-supervised Instance Segmentation	code
ICCV2023	LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation	code
ICCV2023	Enhanced Soft Label for Semi-Supervised Semantic Segmentation	code
ICCV2023	Stochastic Segmentation with Conditional Categorical Diffusion Models	code
CVPR2022	Deep Hierarchical Semantic Segmentation	code
CVPR2022	Rethinking Semantic Segmentation: A Prototype View	code
CVPR2022	Sparse Instance Activation for Real-Time Instance Segmentation	code
CVPR2022	Instance Segmentation with Mask-supervised Polygonal Boundary Transformers	code
CVPR2022	CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation	None
CVPR2022	Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers	None
CVPR2022	PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation	code
CVPR2022	Mask Transfiner for High-Quality Instance Segmentation	code
CVPR2022	Unsupervised Hierarchical Semantic Segmentation With Multiview Cosegmentation and Clustering Transformers	None
CVPR2022	Coarse-To-Fine Feature Mining for Video Semantic Segmentation	code
CVPR2022	Sparse Object-Level Supervision for Instance Segmentation With Pixel Embeddings	code
CVPR2022	Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation	None
CVPR2022	Pin the Memory: Learning To Generalize Semantic Segmentation	code
CVPR2022	SoftGroup for 3D Instance Segmentation on Point Clouds	code
CVPR2022	SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation	None
CVPR2022	Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement	code
CVPR2022	Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels	code
CVPR2022	Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization	code
CVPR2022	Self-Supervised Learning of Object Parts for Semantic Segmentation	code
CVPR2022	Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation	code
CVPR2022	C-CAM: Causal CAM for Weakly Supervised Semantic Segmentation on Medical Image	code
CVPR2022	Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation	None
CVPR2022	ContrastMask: Contrastive Learning to Segment Every Thing	None
CVPR2022	Generalized Few-Shot Semantic Segmentation	code
CVPR2022	Decoupling Zero-Shot Semantic Segmentation	code
CVPR2022	TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation	code
CVPR2022	Cross-Image Relational Knowledge Distillation for Semantic Segmentation	None
CVPR2022	CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings	code
CVPR2022	GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings	None
CVPR2022	TubeFormer-DeepLab: Video Mask Transformer	None
CVPR2022	Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation	code
CVPR2022	Learning Non-target Knowledge for Few-shot Semantic Segmentation	code
CVPR2022	SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation	code
CVPR2022	Real-Time, Accurate, and Consistent Video Semantic Segmentation via Unsupervised Adaptation and Cross-Unit Deployment on Mobile Device	None
CVPR2022	Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation	code
CVPR2022	Amodal Panoptic Segmentation	code
CVPR2022	Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers	code
CVPR2022	Partial Class Activation Attention for Semantic Segmentation	code
CVPR2022	Weakly Supervised Semantic Segmentation using Out-of-Distribution Data	code
CVPR2022	Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation	None
CVPR2022	Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation	code
CVPR2022	Towards Noiseless Object Contours for Weakly Supervised Semantic	code
CVPR2022	L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation	code
CVPR2022	DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation	code
CVPR2022	Stratified Transformer for 3D Point Cloud Segmentation	code
CVPR2022	GroupViT: Semantic Segmentation Emerges from Text Supervision	code	enlightened
WACV2022	UNETR: Transformers for 3D Medical Image Segmentation	code
WACV2022	Pixel-Level Bijective Matching for Video Object Segmentation	code
WACV2022	A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation	None
WACV2022	Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation	code
WACV2022	Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation	code
WACV2022	Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation	code
WACV2022	Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation	None
WACV2022	Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation	code
WACV2022	AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation	None
WACV2022	Single-shot Path Integrated Panoptic Segmentation	None
WACV2022	Time-Space Transformers for Video Panoptic Segmentation	None
WACV2022	FASSST: Fast Attention Based Single-Stage Segmentation Net for Real-Time Instance Segmentation	None
WACV2022	Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries	None
WACV2022	Co-Net: A Collaborative Region-Contour-Driven Network for Fine-to-Finer Medical Image Segmentation	None
WACV2022	T-Net: A Resource-Constrained Tiny Convolutional Neural Network for Medical Image Segmentation	None
WACV2022	Multi-Domain Incremental Learning for Semantic Segmentation	code
WACV2022	Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images	None
WACV2022	MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation	None
WACV2022	Hyper-Convolution Networks for Biomedical Image Segmentation	code
WACV2022	AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation	None
ICCV2021	Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic Segmentation	code
ICCV2021	Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation	None	enlightened
CVPR2020	Context Prior for Scene Segmentation	code	enlightened
	Deep Transport Network for Unsupervised Video Object Segmentation	None
ICCV2021	TempNet: Online Semantic Segmentation on Large-scale Point Cloud Series	None
ICCV2021	Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation	code
ICCV2021	Region-Aware Contrastive Learning for Semantic Segmentation	None
ICCV2021	Graph Constrained Data Representation Learning for Human Motion Segmentation	code	enlightened
ICCV2021	Motion Segmentation and Tracking using Normalized Cuts	None	enlightened
ICCV2015	Temporal Subspace Clustering for Human Motion Segmentation	None
ICCV2021	Region-aware Contrastive Learning for Semantic Segmentation	None	enlightened
ICCV2021	GP-S3Net: Graph-Based Panoptic Sparse Semantic Segmentation Network	None	enlightened
ICCV2021	Joint Inductive and Transductive Learning for Video Object Segmentation	code
ICCV2021	Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation	None
ICCV2021	FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation	code
ICCV2021	Full-Duplex Strategy for Video Object Segmentation	code
ICCV2021	Robust Trust Region for Weakly Supervised Segmentation	code
ICCV2021	Exploring Cross-Image Pixel Contrast for Semantic Segmentation	code	enlightened
ICCV2021	Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks	code
ICCV2021	Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation	code	enlightened
ICCV2021	Learning With Noisy Labels for Robust Point Cloud Segmentation	None
ICCV2021	Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation	None
ICCV2021	Self-Regulation for Semantic Segmentation	None
ICCV2021	Uncertainty-Aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation	None
ICCV2021	Mining Contextual Information Beyond Image for Semantic Segmentation	code
ICCV2021	Contrastive Learning for Label Efficient Semantic Segmentation	None
ICCV2021	BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation	code
ICCV2021	BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-Domain Semantic Segmentation	code
ICCV2021	RECALL: Replay-based Continual Learning in Semantic Segmentation	code
ICCV2021	Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer	code
ICCV2021	Unlocking the Potential of Ordinary Classifier: Class-specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation	code
ICCV2021	Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation	code
ICCV2021	VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation	code
ICCV2021	ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation	None
ICCV2021	Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation	None
ICCV2021	Complementary Patch for Weakly Supervised Semantic Segmentation	None
ICCV2021	Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation	code
ICCV2021	Deep Metric Learning for Open World Semantic Segmentation	None
ICCV2021	ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation	None
ICCV2021	Geometric Unsupervised Domain Adaptation for Semantic Segmentation	code
ICCV2021	Self-Supervised 3D Hand Pose Estimation from monocular RGB via Contrastive Learning	code	enlightened
ICCV2021	How Shift Equivariance Impacts Metric Learning for Instance Segmentation	code	enlightened
ICCV2021	Personalized Image Semantic Segmentation	code
ICCV2021	Learning Meta-class Memory for Few-Shot Semantic Segmentation	None
ICCV2021	Hierarchical Aggregation for 3D Instance Segmentation	code
ICCV2021	Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation	code
ICCV2021	Segmenter: Transformer for Semantic Segmentation	code
ICCV2021	Multi-Anchor Active Domain Adaptation for Semantic Segmentation	code
ICCV2021	Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation	None	enlightened
ICCV2021	Panoptic Narrative Grounding	code	new task
ICCV2021	Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals	code	enlightened
ICCV2021	Rank & Sort Loss for Object Detection and Instance Segmentation	code
ICCV2021	ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation	code
CVPR2021	Learning Calibrated Medical Image Segmentation via Multi-rater Agreement Modeling	code
CVPR2021	4D Panoptic LiDAR Segmentation	code	new task
CVPR2021	Zero-Shot Instance Segmentation	None	new task
CVPR2021	Learning To Count Everything	code
CVPR2021	Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation	None
CVPR2021	Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation	None
CVPR2021	Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation	code
CVPR2021	Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation	code
CVPR2021	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation	code	data-argu
CVPR2021	A2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation	None
CVPR2021	Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation	code
CVPR2021	BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation	code
CVPR2021	HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation	code
CVPR2021	Point Cloud Instance Segmentation using Probabilistic Embeddings	None	enlightened
CVPR2021	FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter	code
CVPR2021	Background-Aware Pooling and Noise-Aware Loss for Weakly-SupervisedSemantic Segmentation	code
CVPR2021	Hierarchical Lovasz Embeddings for Proposal-free Panoptic Segmentation	None	enlightened
CVPR2021	Learning to Associate Every Segment for Video Panoptic Segmentation	None
CVPR2021	Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds	None
CVPR2021	Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation	code
CVPR2021	DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation	code
CVPR2021	Deeply Shape-guided Cascade for Instance Segmentation	code
CVPR2021	Part-aware Panoptic Segmentation	code	new task
CVPR2021	ColorRL: Reinforced Coloring for End-to-End Instance Segmentation	code	novelty, enlightened
CVPR2021	MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers	code	enlightened
CVPR2021	Fully Convolutional Networks for Panoptic Segmentation	code
CVPR2021	(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network	None
CVPR2021	PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering	code	enlightened
CVPR2021	Learning Dynamic Routing for Semantic Segmentation	code
CVPR2021	PolyTransform: Deep Polygon Transformer for Instance Segmentation	None
CVPR2021	PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation	code
AAAI2022	Learning to Model Pixel-Embedded Affinity for Homogeneous Instance Segmentation	code
AAAI2022	Multi-Knowledge Aggregation and Transfer for Semantic Segmentation	None
AAAI2022	Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentation	None
AAAI2022	Unsupervised Representation for Semantic Segmentation by Implicit Cycle-Attention Contrastive Learning	None
AAAI2022	CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation	None
CVPR2020	BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation	code
CVPR2020	Pixel Consensus Voting for Panoptic Segmentation	code	enlightened
CVPR2020	3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation	None
CVPR2020	PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation	None
CVPR2020	Real-Time Panoptic Segmentation from Dense Detections	None
CVPR2020	Affinity Graph Supervision for Visual Recognition	None
CVPR2020	Spatial Pyramid Based Graph Reasoning for Semantic Segmentation	None
CVPR2020	Bidirectional Graph Reasoning Network for Panoptic Segmentation	None
ECCV2022	OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers	code
ECCV2022	PseudoClick: Interactive Image Segmentation with Click Imitation	None	enlightened
ECCV2022	Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding	None	enlightened
ICLR2022	LABEL-EFFICIENT SEMANTIC SEGMENTATION WITH DIFFUSION MODELS	code	diffusion model
arxiv	Diffusion Models as Plug-and-Play Priors	code
WACV2020	Distributed Iterative Gating Networks for Semantic Segmentation	None
WACV2020	Multi Receptive Field Network for Semantic Segmentation	None
WACV2020	MaskPlus: Improving Mask Generation for Instance Segmentation	None
WACV2020	Efficient Video Semantic Segmentation with Labels Propagation and Refinement	None
WACV2020	Global Context Reasoning for Semantic Segmentation of 3D Point Clouds	None
ICCV2019	Asymmetric Non-local Neural Networks for Semantic Segmentation	code
ICCV2019	CCNet: Criss-Cross Attention for Semantic Segmentation	code
ICCV2019	SSAP: Single-Shot Instance Segmentation With Affinity Pyramid	code	enlightened
ICCV2019	ACE: Adapting to Changing Environments for Semantic Segmentation	None
ICCV2019	Dynamic Multi-scale Filters for Semantic Segmentation	code	draw pic
ICCV2019	Towards Bridging Semantic Gap to Improve Semantic Segmentation	None
ICCV2019	Feature Weighting and Boosting for Few-Shot Segmentation	None
ICCV2019	Explicit Shape Encoding for Real-Time Instance Segmentation	code
ICCV2019	IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of Things	None
ICCV2019	Video Instance Segmentation	None
ICCV2019	Gated-SCNN: Gated Shape CNNs for Semantic Segmentation	None
ICCV2019	Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation	None
ICCV2019	Universal Semi-Supervised Semantic Segmentation	None
ICCV2019	ACFNet: Attentional Class Feature Network for Semantic Segmentation	code
ICCV2019	YOLACT Real-time Instance Segmentation	code
ICCV2019	FCOS: Fully Convolutional One-Stage Object Detection	code
ICCV2019	Semantic Instance Segmentation via Deep Metric Learning	None	enlighten
ECCV2022	SeqFormer: Sequential Transformer for Video Instance Segmentation	code
ECCV2022	On Mitigating Hard Clusters for Face Clustering	code
ECCV2022	CenterFormer: Center-based Transformer for 3D Object Detection	code
ECCV2022	ObjectBox: From Centers to Boxes for Anchor-Free Object Detection	code
ECCV2022	Learning Topological Interactions for Multi-Class Medical Image Segmentation	code
ECCV2022	CAR: Class-aware Regularizations for Semantic Segmentation	code
ECCV2022	Active Pointly-Supervised Instance Segmentation	None
ECCV2022	DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation	code
ECCV2022	Video Mask Transfiner for High-Quality Video Instance Segmentation	code
ECCV2022	Box-supervised Instance Segmentation with Level Set Evolution	code
ECCV2022	Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation	code
ECCV2022	2D Amodal Instance Segmentation Guided by 3D Shape Prior	None	updating
ECCV2022	Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation	None	updating
ECCV2022	CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation	code	enlightened
ECCV2022	Continual Semantic Segmentation via Structure Preserving and Projected Feature Alignment	None
ECCV2022	Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation	code	enlightened
ECCV2022	Learning Implicit Feature Alignment Function for Semantic Segmentation	code
ECCV2022	Open-world Semantic Segmentation via Contrasting and Clustering Vision-language Embedding	None
ECCV2022	RBC: Rectifying the Biased Context in Continual Semantic Segmentation	None
ECCV2022	Panoptic-PartFormer: Learning a Unified model for Panoptic Part Segmentation	code
ECCV2022	Language-Grounded Indoor 3D Semantic Segmentation in the Wild	code	loss enlightened
ECCV2022	Learning with Free Object Segments for Long-Tailed Instance Segmentation
ECCV2022	A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation	code
ICLR2022	Label-Efficient Semantic Segmentation with Diffusion Models	code	diffusion for seg

---

Graph Representation and Cluster

ICME2020	S3NET: GRAPH REPRESENTATIONAL NETWORK FOR SKETCH RECOGNITION	code
NeurIPS2018	Hierarchical Graph Representation Learning with Differentiable Pooling	code or code
NeurIPS2020	DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation	code
ICLR2018	Graph Attention Networks	code
IJCAI2019	DAEGC: Attributed Graph Clustering: A Deep Attentional Embedding Approach	code
ICML2020	Mini-cut: Spectral Clustering with Graph Neural Networks for Graph Pooling	code or code
KDD2019	Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks	code
ICCV2021	Graph Contrastive Clustering	code
ECCV2020	Scan: Learning to classify images without labels	code	enlightened
	Unsupervised Deep Embedding for Clustering Analysis	code
CVPR2022	DeepDPM: Deep Clustering With an Unknown Number of Clusters	code
CVPR2022	Lifelong Graph Learning	code
ICCV2021	Clustering by Maximizing Mutual Information Across Views	None
ICCV2021	Region Similarity Representation Learning	code
AAAI2022	Deep Graph Clustering via Dual Correlation Reduction	code
AAAI2021	Contrastive Clustering	code	enlightened
CVPR2021	Nearest Neighbor Matching for Deep Clustering	code	enlightened
CVPR2020	Deep Semantic Clustering by Partition Confidence Maximisation	code	enlightened
CVPR2021	Deep Fair Clustering for Visual Learning	None
CVPR2021	Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning	code
AAAI2022	GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction	None
AAAI2022	Structure-Aware Transformer for Graph Representation Learning	code
CVPR2020	Large Scale Video Representation Learning via Relational Graph Clustering	None
ECCV2018	Universal Sketch Perceptual Grouping	code	enlightened
WACV2020	MaskPlus: Improving Mask Generation for Instance Segmentation	None
WACV2020	GAR: Graph Assisted Reasoning for Object Detection	None
WACV2020	Differentiable Scene Graphs	code	enlightened
WACV2020	Multi-Level Representation Learning for Deep Subspace Clustering	None
ICCV2019	Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition	code
ECCV2022	On Mitigating Hard Clusters for Face Clustering	code
ECCV2022	Generative Subgraph Contrast for Self-Supervised Graph Representation Learning	code	enlightened
ICLR2022	Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space	code	enlightened

---

Referring Segmentation

CVPR2025	VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos	code
CVPR2025	ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding	code
CVPR2025	VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos	code
CVPR2025	FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression	code
CVPR2025	F-LMM: Grounding Frozen Large Multimodal Models	code
CVPR2024	Generative Region-Language Pretraining for Open-Ended Object Detection	code	√√√, like R-Tex2
CVPR2024	PerceptionGPT: Effectively Fusing Visual Perception into LLM	None	√√√，powerful than LISA, notable
ECCV2024	An Efficient and Effective Transformer Decoder-Based Framework for Multi-task Visual Grounding	code	√√√
ECCV2024	Mask Grounding for Referring Image Segmentation	code	√√√
AAAI2025	ChatterBox: Multi-round Multimodal Referring and Grounding	code
ICLR2024	BARLERIA: AN EFFICIENT TUNING FRAMEWORK FOR REFERRING IMAGE SEGMENTATION	code
CVPR2024	Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation	code
CVPR2024	LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation	None
CVPR2024	Mask Grounding for Referring Image Segmentation	None
CVPR2024	LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation	code
CVPR2024	Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation	code
CVPR2024	Prompt-Driven Referring Image Segmentation with Instance Contrasting	None
CVPR2024	Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation	code
ICCV2021	Vision-Language Transformer and Query Generation for Referring Segmentation	code
CVPR2021	Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation	code
CVPR2021	CRIS: CLIP-Driven Referring Image Segmentation	code
CVPR2022	LAVT: Language-Aware Vision Transformer for Referring Image Segmentation	code
ICCV2021	Vision-Language Transformer and Query Generation for Referring Segmentation	code
CVPR2021	Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation	None
CVPR2021	Bottom-Up Shift and Reasoning for Referring Image Segmentation	code
WACV2020	Leveraging Pretrained Image Classifiers for Language-Based Segmentation	code
ICCV2019	Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding	code
ICCV2019	G3RAPHGROUND: Graph-based Language Grounding	None
ICCV2019	Dynamic Graph Attention for Referring Expression Comprehension	None
ICCV2019	Learning to Assemble Neural Module Tree Networks for Visual Grounding	None
ICCV2019	A Fast and Accurate One-Stage Approach to Visual Grounding	code
ICCV2019	See-Through-Text Grouping for Referring Image Segmentation	None
ECCV2022	UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling	code
ECCV2022	SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding	code
ECCV2022	Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds	code
ICCV2023	Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation	code