SOTAVerified

Semantic Segmentation

Papers

Showing 901925 of 14763 papers

TitleStatusHype
Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image SegmentationCode1
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic SegmentationCode1
CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea SegmentationCode1
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban ScenesCode1
Data Augmentation-free Unsupervised Learning for 3D Point Cloud UnderstandingCode1
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label FusionCode1
Active learning for medical image segmentation with stochastic batchesCode1
Dataset Enhancement with Instance-Level AugmentationsCode1
AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image SegmentationCode1
Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite ImagesCode1
Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised SegmentationCode1
Cross-Layer Retrospective Retrieving via Layer AttentionCode1
Cross-modal Learning for Domain Adaptation in 3D Semantic SegmentationCode1
DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian SplattingCode1
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance SegmentationCode1
DDANet: Dual Decoder Attention Network for Automatic Polyp SegmentationCode1
CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image SegmentationCode1
A Multi-Level Approach to Waste Object SegmentationCode1
UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place SolutionCode1
Decomposed Knowledge Distillation for Class-Incremental Semantic SegmentationCode1
Decomposing 3D Scenes into Objects via Unsupervised Volume SegmentationCode1
D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in VideosCode1
MMOTU: A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic SegmentationCode1
Cross-Domain Few-Shot Semantic SegmentationCode1
Show:102550
← PrevPage 37 of 591Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-H (M3I Pre-training)Params (M)1,310Unverified
2ViT-P (InternImage-H)Validation mIoU63.6Unverified
3ONE-PEACEValidation mIoU63Unverified
4M3I Pre-training (InternImage-H)Validation mIoU62.9Unverified
5InternImage-HValidation mIoU62.9Unverified
6BEiT-3Validation mIoU62.8Unverified
7EVAValidation mIoU62.3Unverified
8ViT-P (OneFormer, InternImage-H)Validation mIoU61.6Unverified
9ViT-Adapter-L (Mask2Former, BEiTv2 pretrain)Validation mIoU61.5Unverified
10FD-SwinV2-GValidation mIoU61.4Unverified