Awesome Weakly-supervised Object Localization

Table of Contents

• 1. Performance
  • 1.1. Top1/5 results on CUB-200-2011 [✓]
    • Transformer
    • VGG
    • InceptionV3
    • Others
  • 1.2. Top1/5 results on ImageNet [✓]
    • Transformer
    • VGG
    • InceptionV3
    • Others
• 2. Paper List
  • 2023 [✓]
  • 2022 [✓]
  • 2021 [✓]
  • 2020 [✓]
  • 2019 [✓]
  • 2018 [✓]
  • 2017 [✓]
  • 2016 [✓]
• 3. Dataset
  • CUB-200-2011
  • ImageNet

Table of contents generated with markdown-toc

Contact [email protected] if any paper is missed!

1. Performance

• Bac. C: backbone for classification
• Bac. L: backbone for localization, does not exist for methods use a single network for classification and localization.
• Top-1/Top-5 CLS: is correct if the Top-1/Top-5 predict categories contain the correct label.
• GT-known Loc is correct when the intersection over union (IoU) between the ground-truth and the prediction is larger than 0.5 and does not consider whether the predicted category is correct.
• Top-1/Top-5 Loc is correct when Top-1/Top-5 CLS and GT-Known LOC are both correct.
• "-" indicates not exist. "?" indicates the corresponding item is not mentioned in the paper.

1.1. Top1/5 results on CUB-200-2011

Transformer

VGG

InceptionV3

Others

1.2. Top1/5 results on ImageNet

Transformer

VGG

InceptionV3

Others

2. Paper List

2023

• GenPromp: 2023ICCV Generative Prompt Model for Weakly Supervised Object Localization
• WEND: 2023ACM MM Rethinking the Localization in Weakly Supervised Object Localization

2022

• CREAM: 2022CVPR CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping
• DA-WSOL: 2022CVPR Weakly Supervised Object Localization as Domain Adaption
• AlignMix: 2022CVPR AlignMix: Improving representation by interpolating aligned features
• ViTOL: 2022CVPRW ViTOL: Vision Transformer for Weakly Supervised Object Localization
• 2022TPAMI Evaluation for Weakly Supervised Object Localization Protocol, Metrics, and Datasets
• 2022TNNLS Diverse Complementary Part Mining for Weakly Supervised Object Localization
• 2022PR Gradient-based refined class activation map for weakly supervised object localization
• 2022TMM Dual-Gradients Localization Framework With Skip-Layer Connections for Weakly Supervised Object Localization
• 2022ICMR FreqCAM: Frequent Class Activation Map for Weakly Supervised Object Localization
• SCM:2022ECCV Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
• 2022arxiv Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization

2021

• SLT-Net: 2021CVPR: Strengthen Learning Tolerance for Weakly Supervised Object Localization
• TS-CAM: 2021ICCV TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
• 2021TIP Multi-Scale Low-Discriminative Feature Reactivation for Weakly Supervised Object Localization
• 2021TIP LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
• 2021PR Region-based dropout with attention prior for weakly supervised object localization
• 2021arxiv Background-aware Classification Activation Map for Weakly Supervised Object Localization
• 2021arxiv MinMaxCAM Improving object coverage for CAM-based Weakly Supervised Object Localization
• 2021arxiv Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection

2020

• PSOL: 2020CVPR Rethinking the Route Towards Weakly Supervised Object Localization
• 2020CVPR Evaluating Weakly Supervised Object Localization Methods Right
• MEIL: 2020CVPR Erasing Integrated Learning A Simple yet Effective Approach for Weakly Supervised Object Localization
• GC-Net: 2020ECCV Geometry Constrained Weakly Supervised Object Localization
• I2C: 2020ECCV Inter-Image Communication for Weakly Supervised Localization
• 2020ECCV Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
• 2020ICPR Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization
• 2020arxiv Rethinking Localization Map Towards Accurate Object Perception with Self-Enhancement Maps

2019

• ADL: 2019CVPR Attention-based Dropout Layer for Weakly Supervised Object Localization
• DANet: 2019ICCV DANet: Divergent Activation for Weakly Supervised Object Localization
• CutMix: 2019ICCV CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• 2019ICLR Marginalized average attentional network for weakly-supervised learning
• 2019arxiv Dual-attention Focused Module for Weakly Supervised Object Localization
• 2019arxiv Weakly Supervised Localization Using Background Images
• 2019arxiv Weakly Supervised Object Localization with Inter-Intra Regulated CAMs

2018

• ACoL: 2018CVPR Adversarial Complementary Learning for Weakly Supervised Object Localization
• SPG: 2018ECCV Self-produced Guidance for Weakly-supervised Object Localization

2017

• Grad-CAM: 2017ICCV Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• HaS: 2017ICCV Hide-and-Seek Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization

2016

• CAM: 2016CVPR Learning Deep Features for Discriminative Localization

3. Dataset

CUB-200-2011

@article{wah2011caltech,
 title={The caltech-ucsd birds-200-2011 dataset},
 author={Wah, Catherine and Branson, Steve and Welinder, Peter and Perona, Pietro and Belongie, Serge},
 year={2011},
 publisher={California Institute of Technology}
}

ImageNet

@inproceedings{deng2009imagenet,
  title={Imagenet: A large-scale hierarchical image database},
  author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
  booktitle={2009 IEEE conference on computer vision and pattern recognition},
  pages={248--255},
  year={2009},
  organization={Ieee}
}