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.
PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization
TeD-Loc: Text Distillation for Weakly Supervised Object Localization
Categorical Knowledge Fused Recognition: Fusing Hierarchical Knowledge with Image Classification through Aligning and Deep Metric Learning
Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos
Leveraging Activations for Superpixel Explanations
SE3D: A Framework For Saliency Method Evaluation In 3D Imaging
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology
Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label
A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
Towards Two-Stream Foveation-based Active Vision Learning
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective
Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization
DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization
Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization
Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization
Rethinking the Localization in Weakly Supervised Object Localization
Generative Prompt Model for Weakly Supervised Object Localization
Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization
Open-World Weakly-Supervised Object Localization
Spatial-Aware Token for Weakly Supervised Object Localization
Knowledge-guided Causal Intervention for Weakly-supervised Object Localization
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
Dual Progressive Transformations for Weakly Supervised Semantic Segmentation
Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization
Re-Attention Transformer for Weakly Supervised Object Localization
Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
On Label Granularity and Object Localization
Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization
CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping
Location-free Human Pose Estimation
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition
ViTOL: Vision Transformer for Weakly Supervised Object Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.