SOTAVerified

Object Discovery

Object Discovery is the task of identifying previously unseen objects.

Source: Unsupervised Object Discovery and Segmentation of RGBD-images

Papers

Showing 76100 of 210 papers

TitleStatusHype
Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields0
Zero-Shot Object-Centric Representation Learning0
XS-VID: An Extremely Small Video Object Detection Dataset0
Guided Latent Slot Diffusion for Object-Centric Learning0
PEEKABOO: Hiding parts of an image for unsupervised object localizationCode0
Rethinking Image-to-Video Adaptation: An Object-centric Perspective0
Towards Open-set Camera 3D Object Detection0
Adaptive Slot Attention: Object Discovery with Dynamic Slot NumberCode0
Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset0
Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection0
Recurrent Complex-Weighted Autoencoders for Unsupervised Object DiscoveryCode0
Masked Multi-Query Slot Attention for Unsupervised Object DiscoveryCode0
Label-Efficient 3D Object Detection For Road-Side Units0
Co-Occurring of Object Detection and Identification towards unlabeled object discovery0
LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT DescriptorsCode0
Attention-Guided Masked Autoencoders For Learning Image Representations0
Unsupervised Discovery of Object-Centric Neural Fields0
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations0
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping0
Has Anything Changed? 3D Change Detection by 2D Segmentation Masks0
Unsupervised Musical Object Discovery from AudioCode0
The Background Also Matters: Background-Aware Motion-Guided Objects Discovery0
Towards Unsupervised Object Detection From LiDAR Point Clouds0
SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics0
Sub-token ViT Embedding via Stochastic Resonance TransformersCode0
Show:102550
← PrevPage 4 of 9Next →

No leaderboard results yet.