SOTAVerified

Object Discovery

Object Discovery is the task of identifying previously unseen objects.

Source: Unsupervised Object Discovery and Segmentation of RGBD-images

Papers

Showing 2650 of 210 papers

TitleStatusHype
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?Code1
OCAtari: Object-Centric Atari 2600 Reinforcement Learning EnvironmentsCode1
Object-Centric Learning for Real-World Videos by Predicting Temporal Feature SimilaritiesCode1
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual GroupingCode1
Object Discovery from Motion-Guided TokensCode1
Invariant Slot Attention: Object Discovery with Slot-Centric Reference FramesCode1
Unsupervised Object Localization: Observing the Background to Discover ObjectsCode1
Discovering A Variety of Objects in Spatio-Temporal Human-Object InteractionsCode1
MOVE: Unsupervised Movable Object Segmentation and DetectionCode1
4D Unsupervised Object DiscoveryCode1
Object Discovery via Contrastive Learning for Weakly Supervised Object DetectionCode1
Unsupervised Semantic Segmentation with Self-supervised Object-centric RepresentationsCode1
Self-Supervised Visual Representation Learning with Semantic GroupingCode1
Complex-Valued Autoencoders for Object DiscoveryCode1
Test-time Adaptation with Slot-Centric ModelsCode1
Unsupervised Domain Adaptation for Nighttime Aerial TrackingCode1
Discovering Objects that Can MoveCode1
What Matters For Meta-Learning Vision Regression Tasks?Code1
Monocular Arbitrary Moving Object Discovery and SegmentationCode1
Learning Co-segmentation by Segment Swapping for Retrieval and DiscoveryCode1
Localizing Objects with Self-Supervised Transformers and no LabelsCode1
Learning to Track Objects from Unlabeled VideosCode1
Learning Open-World Object Proposals without Learning to ClassifyCode1
Large-Scale Unsupervised Object DiscoveryCode1
Unsupervised Layered Image Decomposition into Object PrototypesCode1
Show:102550
← PrevPage 2 of 9Next →

No leaderboard results yet.