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.
Total Variation Optimization Layers for Computer Vision
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
HINT: Hierarchical Neuron Concept Explainer
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization
Weakly Supervised Object Localization as Domain Adaption
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization
Background-aware Classification Activation Map for Weakly Supervised Object Localization
LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization
Background Activation Suppression for Weakly Supervised Object Localization
Group-Wise Learning for Weakly Supervised Semantic Segmentation
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost
Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization
Localizing Objects with Self-Supervised Transformers and no Labels
F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling
Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection
Shallow Feature Matters for Weakly Supervised Object Localization
Normalization Matters in Weakly Supervised Object Localization
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
Keep CALM and Improve Visual Feature Attribution
Improving Few-shot Learning with Weakly-supervised Object Localization
MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
Improving Weakly-supervised Object Localization via Causal Intervention
Weakly Supervised Object Localization and Detection: A Survey
Fine-Grained Attention for Weakly Supervised Object Localization
DAP: Detection-Aware Pre-training with Weak Supervision
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
Hierarchical Complementary Learning for Weakly Supervised Object Localization
LID 2020: The Learning from Imperfect Data Challenge Results
Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.