Skip to content

Latest commit

 

History

History
44 lines (35 loc) · 1.36 KB

README.md

File metadata and controls

44 lines (35 loc) · 1.36 KB

Revisiting CAM

We prove the CAM method can be simplified to enable end-to-end training. The proof refers to Section 3.1.

The proposed ACoL method

We apply two classifiers to discover complementary regions of target objects.

Localization

Effect of mining complementary regions

Prerequisites

  • Python2.7
  • PyTorch
  • tqdm

Data Preparation

  • Download the ILSVRC dataset and save them to $data$

Train

git clone https://github.com/xiaomengyc/ACoL.git
cd ACoL
mkdir snapshots
cd scripts
bash train_vgg_imagenet.sh

Citation

If you find this code helpful, please consider to cite this paper:

@inproceedings{zhang2018adversarial,
  title={Adversarial complementary learning for weakly supervised object localization},
  author={Zhang, Xiaolin and Wei, Yunchao and Feng, Jiashi and Yang, Yi and Huang, Thomas},
  booktitle={IEEE CVPR},
  year={2018}
}