SOTAVerified

Segmentation

Papers

Showing 6170 of 13072 papers

TitleStatusHype
Rethinking the Evaluation of Visible and Infrared Image FusionCode3
SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable MannersCode3
InstanSeg: an embedding-based instance segmentation algorithm optimized for accurate, efficient and portable cell segmentationCode3
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image SegmentationCode3
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition TasksCode3
Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2Code3
EAFormer: Scene Text Segmentation with Edge-Aware TransformersCode3
VISA: Reasoning Video Object Segmentation via Large Language ModelsCode3
xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba CounterpartCode3
Segment Anything without SupervisionCode3
Show:102550
← PrevPage 7 of 1308Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1unSAM+ (Semi-supervised)Average Precision42.8Unverified
2SAMAverage Precision38.9Unverified
#ModelMetricClaimedVerifiedStatus
1HNN10%20Unverified
#ModelMetricClaimedVerifiedStatus
1ABANetF1 Score96.82Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50 + DeepLabV3+F1 score0.77Unverified
#ModelMetricClaimedVerifiedStatus
1LangGasIoU0.69Unverified