Papers with Code 아카이브
Object Discovery
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Object Discovery is the task of identifying previously unseen objects.
Source: Unsupervised Object Discovery and Segmentation of RGBD-images
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Multi-Label Self-Supervised Learning with Scene Images
Grounded Object Centric Learning
Multi-Object Discovery by Low-Dimensional Object Motion
FODVid: Flow-guided Object Discovery in Videos
Weakly-supervised Contrastive Learning for Unsupervised Object Discovery
OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
Coarse Is Better? A New Pipeline Towards Self-Supervised Learning with Uncurated Images
Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
Cycle Consistency Driven Object Discovery
Contrastive Training of Complex-Valued Autoencoders for Object Discovery
SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
AutoRecon: Automated 3D Object Discovery and Reconstruction
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
MOST: Multiple Object localization with Self-supervised Transformers for object discovery
Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots
Object Discovery from Motion-Guided Tokens
DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery
Universal Instance Perception as Object Discovery and Retrieval
Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
Image Segmentation-based Unsupervised Multiple Objects Discovery
Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy
Unsupervised Object Localization: Observing the Background to Discover Objects
Boosting Object Representation Learning via Motion and Object Continuity
Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions
Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers
MOVE: Unsupervised Movable Object Segmentation and Detection
Object-Category Aware Reinforcement Learning
4D Unsupervised Object Discovery
Differentiable Mathematical Programming for Object-Centric Representation Learning
Motion-inductive Self-supervised Object Discovery in Videos
Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut
Objects Can Move: 3D Change Detection by Geometric Transformation Constistency
Object Discovery via Contrastive Learning for Weakly Supervised Object Detection
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.