Papers with Code 아카이브
Weakly Supervised Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 17
- 보존된 평가 기록
- 139
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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning
Weakly Supervised Cascaded Convolutional Networks
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
Weakly supervised object detection using pseudo-strong labels
Self Paced Deep Learning for Weakly Supervised Object Detection
Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection
Weakly Supervised Localization using Deep Feature Maps
ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks
Weakly Supervised Deep Detection Networks
Contextual Action Recognition with R*CNN
On learning to localize objects with minimal supervision
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.