SOTAVerified

Semantic Segmentation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 401–450 of 14763 papers

TitleStatusHype
ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image SegmentationCode2
SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian DecompositionCode2
MF-MOS: A Motion-Focused Model for Moving Object SegmentationCode2
MouSi: Poly-Visual-Expert Vision-Language ModelsCode2
SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion NetworksCode2
Vivim: a Video Vision Mamba for Medical Video SegmentationCode2
Rethinking Patch Dependence for Masked AutoencodersCode2
Tyche: Stochastic In-Context Learning for Medical Image SegmentationCode2
Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural CalibrationCode2
PA-SAM: Prompt Adapter SAM for High-Quality Image SegmentationCode2
Exploring Color Invariance through Image-Level Ensemble LearningCode2
A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask InpaintingCode2
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelCode2
Adversarial Supervision Makes Layout-to-Image Diffusion Models ThriveCode2
OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box PromptsCode2
UV-SAM: Adapting Segment Anything Model for Urban Village IdentificationCode2
PMFSNet: Polarized Multi-scale Feature Self-attention Network For Lightweight Medical Image SegmentationCode2
Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imageryCode2
Seg-metrics: a Python package to compute segmentation metricsCode2
PartSTAD: 2D-to-3D Part Segmentation Task AdaptationCode2
Deep Covariance Alignment for Domain Adaptive Remote Sensing Image SegmentationCode2
U-Mamba: Enhancing Long-range Dependency for Biomedical Image SegmentationCode2
ODIN: A Single Model for 2D and 3D SegmentationCode2
ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic SegmentationCode2
From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic SegmentationCode2
MRFS: Mutually Reinforcing Image Fusion and SegmentationCode2
LiSA: LiDAR Localization with Semantic AwarenessCode2
Learn to Rectify the Bias of CLIP for Unsupervised Semantic SegmentationCode2
BRAU-Net++: U-Shaped Hybrid CNN-Transformer Network for Medical Image SegmentationCode2
Segment Any Event Streams via Weighted Adaptation of Pivotal TokensCode2
Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse PromptsCode2
SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time SegmentationCode2
Learning Vision from Models Rivals Learning Vision from DataCode2
Unsupervised Universal Image SegmentationCode2
UniRef++: Segment Every Reference Object in Spatial and Temporal SpacesCode2
Narrowing the semantic gaps in U-Net with learnable skip connections: The case of medical image segmentationCode2
SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion ProcessCode2
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentationCode2
Agent Attention: On the Integration of Softmax and Linear AttentionCode2
MCANet: Medical Image Segmentation with Multi-Scale Cross-Axis AttentionCode2
ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical ImageCode2
ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control SystemsCode2
Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic SegmentationCode2
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature FieldsCode2
SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary ConstraintsCode2
Hulk: A Universal Knowledge Translator for Human-Centric TasksCode2
TransNeXt: Robust Foveal Visual Perception for Vision TransformersCode2
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose EstimationCode2
Adapter is All You Need for Tuning Visual TasksCode2
OneFormer3D: One Transformer for Unified Point Cloud SegmentationCode2
Show:102550
← PrevPage 9 of 296Next →
All datasetsADE20KNYU-Depth V2Cityscapes testCityscapes valADE20K valPASCAL ContextS3DIS Area5PASCAL VOC 2012 testS3DISScanNetSUN-RGBDDensePASS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-H (M3I Pre-training)Params (M)1,310—Unverified
2ViT-P (InternImage-H)Validation mIoU63.6—Unverified
3ONE-PEACEValidation mIoU63—Unverified
4M3I Pre-training (InternImage-H)Validation mIoU62.9—Unverified
5InternImage-HValidation mIoU62.9—Unverified
6BEiT-3Validation mIoU62.8—Unverified
7EVAValidation mIoU62.3—Unverified
8ViT-P (OneFormer, InternImage-H)Validation mIoU61.6—Unverified
9ViT-Adapter-L (Mask2Former, BEiTv2 pretrain)Validation mIoU61.5—Unverified
10FD-SwinV2-GValidation mIoU61.4—Unverified