SOTAVerified

Semantic Segmentation

Papers

Showing 32263250 of 14763 papers

TitleStatusHype
CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time SegmentationCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Video Class Agnostic Segmentation with Contrastive Learning for Autonomous DrivingCode1
PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and BeyondCode1
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image RecognitionCode1
Beyond pixel-wise supervision for segmentation: A few global shape descriptors might be surprisingly good!Code1
ISTR: End-to-End Instance Segmentation with TransformersCode1
Robust 3D Cell Segmentation: Extending the View of CellposeCode1
Self-supervised Augmentation Consistency for Adapting Semantic SegmentationCode1
SegmentMeIfYouCan: A Benchmark for Anomaly SegmentationCode1
Emerging Properties in Self-Supervised Vision TransformersCode1
Decoupled Dynamic Filter NetworksCode1
DeepSatData: Building large scale datasets of satellite images for training machine learning modelsCode1
Exploring Relational Context for Multi-Task Dense PredictionCode1
LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR ImagesCode1
Domain Adaptive Semantic Segmentation with Self-Supervised Depth EstimationCode1
Twins: Revisiting the Design of Spatial Attention in Vision TransformersCode1
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory BankCode1
Rethinking BiSeNet For Real-time Semantic SegmentationCode1
Vision Transformers with Patch DiversificationCode1
MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep LearningCode1
UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D EnvironmentsCode1
NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and ColonoscopyCode1
All Tokens Matter: Token Labeling for Training Better Vision TransformersCode1
DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic SegmentationCode1
Show:102550
← PrevPage 130 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