SOTAVerified

Image Segmentation

Image Segmentation is a computer vision task that involves dividing an image into multiple segments or regions, each of which corresponds to a different object or part of an object. The goal of image segmentation is to assign a unique label or category to each pixel in the image, so that pixels with similar attributes are grouped together.

Papers

Showing 2650 of 5035 papers

TitleStatusHype
Segment Anything in Medical ImagesCode4
Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and SegmentationCode4
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense PredictionCode4
Highly Accurate Dichotomous Image SegmentationCode4
Detectron2 Object Detection & Manipulating Images using CartoonizationCode4
No time to train! Training-Free Reference-Based Instance SegmentationCode3
ConceptAttention: Diffusion Transformers Learn Highly Interpretable FeaturesCode3
How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?Code3
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG GenerationCode3
Interactive Medical Image Segmentation: A Benchmark Dataset and BaselineCode3
ZIM: Zero-Shot Image Matting for AnythingCode3
Breaking reCAPTCHAv2Code3
A Short Review and Evaluation of SAM2's Performance in 3D CT Image SegmentationCode3
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image SegmentationCode3
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
Point-SAM: Promptable 3D Segmentation Model for Point CloudsCode3
RobustSAM: Segment Anything Robustly on Degraded ImagesCode3
VISTA3D: Versatile Imaging SegmenTation and Annotation model for 3D Computed TomographyCode3
EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image SegmentationCode3
How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything ModelCode3
SegFormer3D: an Efficient Transformer for 3D Medical Image SegmentationCode3
UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion SegmentationCode3
Segment Any Medical Model ExtendedCode3
PSALM: Pixelwise SegmentAtion with Large Multi-Modal ModelCode3
Show:102550
← PrevPage 2 of 202Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SAM2-UNetIoU0.92Unverified
2HetNetIoU0.83Unverified
3PMDIoU0.82Unverified
4SANetIoU0.8Unverified
5MirrorNetIoU0.79Unverified
#ModelMetricClaimedVerifiedStatus
1SAM2-UNetIoU0.73Unverified
2HetNetIoU0.69Unverified
3SANetIoU0.67Unverified
4PMDIoU0.66Unverified
5MirrorNetIoU0.59Unverified
#ModelMetricClaimedVerifiedStatus
1SAM2-UNetmIoU0.8Unverified
2MAS-SAMmIoU0.79Unverified
3MASNetmIoU0.74Unverified
4ZoomNetmIoU0.74Unverified
#ModelMetricClaimedVerifiedStatus
1HIPIE (ViT-H)mIoUPartS63.8Unverified
2PPSmIoUPartS58.6Unverified
3HIPIE (ResNet-50)mIoUPartS57.2Unverified
4JPPFmIoUPartS54.4Unverified
#ModelMetricClaimedVerifiedStatus
1MAS-SAMmIoU0.74Unverified
2SAM2-UNetmIoU0.74Unverified
3MASNetmIoU0.73Unverified
4ZoomNetmIoU0.73Unverified
#ModelMetricClaimedVerifiedStatus
1OneNete,4-CmIoU63.6Unverified
2OneNete,4-SmAP0.552.75Unverified
3OneNeted,4mIoU14.9Unverified
#ModelMetricClaimedVerifiedStatus
1UNetRDice0.98Unverified
2PALEDDice0.98Unverified
#ModelMetricClaimedVerifiedStatus
1ResAttUNetIoU0.67Unverified
2UNetIoU0.57Unverified
#ModelMetricClaimedVerifiedStatus
1SynCo (ResNet-50) 200epmask AP35.4Unverified
#ModelMetricClaimedVerifiedStatus
1MobileOne-S0GFLOPs0.28Unverified
#ModelMetricClaimedVerifiedStatus
1OneNete,4mIoU6.6Unverified
#ModelMetricClaimedVerifiedStatus
1OneNete,4-CDice Score0.97Unverified