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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 5035 papers

TitleStatusHype
SAM 2: Segment Anything in Images and VideosCode11
Efficient MedSAMs: Segment Anything in Medical Images on LaptopCode7
Bilateral Reference for High-Resolution Dichotomous Image SegmentationCode7
U-Net v2: Rethinking the Skip Connections of U-Net for Medical Image SegmentationCode6
Track Anything: Segment Anything Meets VideosCode5
Segment Anything Model for Medical Image Segmentation: Current Applications and Future DirectionsCode5
Faster Segment Anything: Towards Lightweight SAM for Mobile ApplicationsCode5
Unleashing the Potential of SAM2 for Biomedical Images and Videos: A SurveyCode5
Segment Anything for Videos: A Systematic SurveyCode5
SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and MoreCode5
Segment AnythingCode5
Segment Anything in Medical ImagesCode4
Image Segmentation Keras : Implementation of Segnet, FCN, UNet, PSPNet and other models in KerasCode4
SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image SegmentationCode4
Highly Accurate Dichotomous Image SegmentationCode4
Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and SegmentationCode4
Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image SegmentationCode4
Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image SegmentationCode4
3D TransUNet: Advancing Medical Image Segmentation through Vision TransformersCode4
Your ViT is Secretly an Image Segmentation ModelCode4
Detectron2 Object Detection & Manipulating Images using CartoonizationCode4
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense PredictionCode4
Kolmogorov-Arnold Convolutions: Design Principles and Empirical StudiesCode4
Medical SAM 2: Segment medical images as video via Segment Anything Model 2Code4
The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One ShotCode4
Semantic-SAM: Segment and Recognize Anything at Any GranularityCode4
Attention on the SphereCode4
LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and EditingCode4
Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image SegmentationCode4
VM-UNet: Vision Mamba UNet for Medical Image SegmentationCode4
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?Code3
Segment Any Medical Model ExtendedCode3
SAM-Med2DCode3
SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and MoreCode3
SegFormer3D: an Efficient Transformer for 3D Medical Image SegmentationCode3
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image SegmentationCode3
RobustSAM: Segment Anything Robustly on Degraded ImagesCode3
SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masksCode3
Segment Anything without SupervisionCode3
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360degCode3
MedSegDiff-V2: Diffusion based Medical Image Segmentation with TransformerCode3
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic ModelCode3
No time to train! Training-Free Reference-Based Instance SegmentationCode3
Point-SAM: Promptable 3D Segmentation Model for Point CloudsCode3
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360^Code3
ConceptAttention: Diffusion Transformers Learn Highly Interpretable FeaturesCode3
Breaking reCAPTCHAv2Code3
MA-Net: A Multi-Scale Attention Network for Liver and Tumor SegmentationCode3
Medical SAM Adapter: Adapting Segment Anything Model for Medical Image SegmentationCode3
PSALM: Pixelwise SegmentAtion with Large Multi-Modal ModelCode3
Show:102550
← PrevPage 1 of 101Next →
All datasetsMSD (Mirror Segmentation Dataset)PMDMAS3KPascal Panoptic PartsRMASPASCAL VOCHuTu 80MARIDACOCO val2017ImageNetMSD HeartOxfordPets

Benchmark Results

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