SOTAVerified

Object Discovery

Object Discovery is the task of identifying previously unseen objects.

Source: Unsupervised Object Discovery and Segmentation of RGBD-images

Papers

Showing 151–175 of 210 papers

TitleStatusHype
Image Segmentation-based Unsupervised Multiple Objects Discovery—0
Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy—0
Incremental Object Discovery in Time-Varying Image Collections—0
Individuation, Identification and Object Discovery—0
Inducing Meaningful Units from Character Sequences with Dynamic Capacity Slot Attention—0
Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral Clustering for Unsupervised Segmentation in Videos—0
Iterative Spectral Clustering for Unsupervised Object Localization—0
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions—0
K-means for unsupervised instance segmentation using a self-supervised transformer—0
Label-Efficient 3D Object Detection For Road-Side Units—0
Language-Mediated, Object-Centric Representation Learning—0
Large Scale Novel Object Discovery in 3D—0
Large-Scale Object Mining for Object Discovery from Unlabeled Video—0
Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection—0
Leveraging Registers in Vision Transformers for Robust Adaptation—0
Mining And-Or Graphs for Graph Matching and Object Discovery—0
MOST: Multiple Object localization with Self-supervised Transformers for object discovery—0
Motion-inductive Self-supervised Object Discovery in Videos—0
Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset—0
Multi-Label Self-Supervised Learning with Scene Images—0
Multi-Object Discovery by Low-Dimensional Object Motion—0
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations—0
Object-Category Aware Reinforcement Learning—0
Object Discovery in Videos as Foreground Motion Clustering—0
Object Discovery via Cohesion Measurement—0
Show:102550
← PrevPage 7 of 9Next →

No leaderboard results yet.