SOTAVerified

Segmentation

Papers

Showing 101150 of 13072 papers

TitleStatusHype
SAM3D: Segment Anything in 3D ScenesCode3
VISA: Reasoning Video Object Segmentation via Large Language ModelsCode3
Nuclei instance segmentation and classification in histopathology images with StarDistCode3
nnInteractive: Redefining 3D Promptable SegmentationCode3
EAFormer: Scene Text Segmentation with Edge-Aware TransformersCode3
No time to train! Training-Free Reference-Based Instance SegmentationCode3
Moving Object Segmentation: All You Need Is SAM (and Flow)Code3
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic ModelCode3
MTP: Advancing Remote Sensing Foundation Model via Multi-Task PretrainingCode3
EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image SegmentationCode3
OneFormer: One Transformer to Rule Universal Image SegmentationCode3
A Simple Framework for Open-Vocabulary Segmentation and DetectionCode3
InstanSeg: an embedding-based instance segmentation algorithm optimized for accurate, efficient and portable cell segmentationCode3
Point-SAM: Promptable 3D Segmentation Model for Point CloudsCode3
MA-Net: A Multi-Scale Attention Network for Liver and Tumor SegmentationCode3
Hi-SAM: Marrying Segment Anything Model for Hierarchical Text SegmentationCode3
How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything ModelCode3
GroundGrid:LiDAR Point Cloud Ground Segmentation and Terrain EstimationCode3
SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masksCode3
Tracking Anything with Decoupled Video SegmentationCode3
RevSAM2: Prompt SAM2 for Medical Image Segmentation via Reverse-Propagation without Fine-tuningCode2
Fully Convolutional Instance-aware Semantic SegmentationCode2
From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic SegmentationCode2
FRNet: Frustum-Range Networks for Scalable LiDAR SegmentationCode2
Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic SegmentationCode2
A large annotated medical image dataset for the development and evaluation of segmentation algorithmsCode2
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anythingCode2
Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-trainCode2
FOCUS: Towards Universal Foreground SegmentationCode2
FreeSOLO: Learning to Segment Objects without AnnotationsCode2
FocalClick: Towards Practical Interactive Image SegmentationCode2
FM-Fusion: Instance-aware Semantic Mapping Boosted by Vision-Language Foundation ModelsCode2
Focal Modulation NetworksCode2
FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor SynthesisCode2
Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary SegmentationCode2
FedFMS: Exploring Federated Foundation Models for Medical Image SegmentationCode2
Find Any Part in 3DCode2
AgileFormer: Spatially Agile Transformer UNet for Medical Image SegmentationCode2
FEC: Fast Euclidean Clustering for Point Cloud SegmentationCode2
Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object SegmentationCode2
Fast Online Object Tracking and Segmentation: A Unifying ApproachCode2
FastInst: A Simple Query-Based Model for Real-Time Instance SegmentationCode2
FastSurfer-HypVINN: Automated sub-segmentation of the hypothalamus and adjacent structures on high-resolutional brain MRICode2
FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action SegmentationCode2
FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image SegmentationCode2
F-LMM: Grounding Frozen Large Multimodal ModelsCode2
Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation FrameworkCode2
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
EM-Net: Efficient Channel and Frequency Learning with Mamba for 3D Medical Image SegmentationCode2
Show:102550
← PrevPage 3 of 262Next →

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