SOTAVerified

Universal Segmentation

Universal segmentation is a challenging computer vision task that aims to segment images into semantic regions, regardless of the task or the domain. It requires the model to learn a wide range of visual concepts and to be able to generalize to new tasks and domains.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 32 papers

TitleStatusHype
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and UnderstandingCode5
OneFormer: One Transformer to Rule Universal Image SegmentationCode3
Rethinking the Evaluation of Visible and Infrared Image FusionCode3
FOCUS: Towards Universal Foreground SegmentationCode2
Hierarchical Open-vocabulary Universal Image SegmentationCode2
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual PerceiverCode2
HyperSeg: Towards Universal Visual Segmentation with Large Language ModelCode2
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language ModelsCode2
Large Language Model with Region-guided Referring and Grounding for CT Report GenerationCode2
Masked-attention Mask Transformer for Universal Image SegmentationCode2
SemiSAM+: Rethinking Semi-Supervised Medical Image Segmentation in the Era of Foundation ModelsCode2
MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal ModelCode2
The Missing Point in Vision Transformers for Universal Image SegmentationCode2
One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text PromptsCode2
Unsupervised Universal Image SegmentationCode2
Universal Segmentation at Arbitrary Granularity with Language InstructionCode2
UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation LearnerCode1
MedicoSAM: Towards foundation models for medical image segmentationCode1
CLUSTSEG: Clustering for Universal SegmentationCode1
SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography ImagesCode1
Segment Everything Everywhere All at OnceCode1
VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with LanguageCode0
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal SegmentationCode0
RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT AnalysisCode0
Training a universal instance segmentation network for live cell images of various cell types and imaging modalitiesCode0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.