https://github.com/seqam-lab/alwod
공식 코드ALWOD: Active Learning for Weakly-Supervised Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Weakly Supervised Object Detection (WSOD) is the task of training object detectors with only image tag supervisions.
<span style="color:grey; opacity: 0.6">( Image credit: Soft Proposal Networks for Weakly Supervised Object Localization )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
ALWOD: Active Learning for Weakly-Supervised Object Detection
HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection
SIOD: Single Instance Annotated Per Category Per Image for Object Detection
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
Weakly Supervised Object Detection for Automatic Tooth-marked Tongue Recognition
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
Multiple Instance Detection Network with Online Instance Classifier Refinement
Multiple Instance Detection Network with Online Instance Classifier Refinement
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
Soft Proposal Networks for Weakly Supervised Object Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.