Papers with Code 아카이브
Weakly-Supervised Object Localization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 7
- 보존된 평가 기록
- 30
Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Two-Phase Learning for Weakly Supervised Object Localization
Object-Extent Pooling for Weakly Supervised Single-Shot Localization
How hard can it be? Estimating the difficulty of visual search in an image
Training object class detectors with click supervision
Deep Self-Taught Learning for Weakly Supervised Object Localization
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
Weakly Supervised Object Localization Using Things and Stuff Transfer
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
Weakly Supervised Object Localization Using Size Estimates
Improving Weakly-Supervised Object Localization By Micro-Annotation
Self-Transfer Learning for Fully Weakly Supervised Object Localization
Learning Deep Features for Discriminative Localization
Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
Density-Based Region Search with Arbitrary Shape for Object Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.