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.
SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding
TUSK: Task-Agnostic Unsupervised Keypoints
Self-Supervised Visual Representation Learning with Semantic Grouping
Complex-Valued Autoencoders for Object Discovery
Test-time Adaptation with Slot-Centric Models
Unsupervised Domain Adaptation for Nighttime Aerial Tracking
Discovering Objects that Can Move
Object discovery and representation networks
Towards Self-Supervised Learning of Global and Object-Centric Representations
What Matters For Meta-Learning Vision Regression Tasks?
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
Unsupervised Image Decomposition with Phase-Correlation Networks
Localizing Objects with Self-Supervised Transformers and no Labels
Learning to Track Objects from Unlabeled Videos
Learning Open-World Object Proposals without Learning to Classify
SCOD: Active Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences
Exploring Depth Contribution for Camouflaged Object Detection
PatchNet: Unsupervised Object Discovery based on Patch Embedding
Large-Scale Unsupervised Object Discovery
Unsupervised Layered Image Decomposition into Object Prototypes
Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation
Track, Check, Repeat: An EM Approach to Unsupervised Tracking
Knowledge-Guided Object Discovery with Acquired Deep Impressions
Self-Supervision by Prediction for Object Discovery in Videos
Inducing Meaningful Units from Character Sequences with Dynamic Capacity Slot Attention
GO-Finder: A Registration-Free Wearable System for Assisting Users in Finding Lost Objects via Hand-Held Object Discovery
Language-Mediated, Object-Centric Representation Learning
Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral Clustering for Unsupervised Segmentation in Videos
Chair Segments: A Compact Benchmark for the Study of Object Segmentation
Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
Unsupervised Discovery of 3D Physical Objects from Video
Reconstruction Bottlenecks in Object-Centric Generative Models
Toward unsupervised, multi-object discovery in large-scale image collections
Object-Centric Learning with Slot Attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.