https://github.com/jazzsaxmafia/Weakly_detector

Tensorflow implementation of "Learning Deep Features for Discriminative Localization"
https://github.com/jazzsaxmafia/Weakly_detector

Last synced: about 2 months ago
JSON representation

Tensorflow implementation of "Learning Deep Features for Discriminative Localization"

• Host: GitHub
• URL: https://github.com/jazzsaxmafia/Weakly_detector
• Owner: jazzsaxmafia
• Created: 2016-04-09T04:51:08.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2017-07-29T16:58:03.000Z (over 7 years ago)
• Last Synced: 2024-08-01T08:11:39.086Z (4 months ago)
• Language: Jupyter Notebook
• Size: 2.38 MB
• Stars: 361
• Watchers: 17
• Forks: 87
• Open Issues: 12
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-tensorflow - Weakly_detector - Implementation of ["Learning Deep Features for Discriminative Localization"](http://cnnlocalization.csail.mit.edu/) (Models/Projects)
• Awesome-TensorFlow-Chinese - Weakly_detector - Implementation of ["Learning Deep Features for Discriminative Localization"](http://cnnlocalization.csail.mit.edu/) (模型项目 / 微信群)
• awesome-tensorflow - Weakly_detector - Implementation of ["Learning Deep Features for Discriminative Localization"](http://cnnlocalization.csail.mit.edu/) (Models/Projects)
• fucking-awesome-tensorflow - Weakly_detector - Implementation of ["Learning Deep Features for Discriminative Localization"](http://cnnlocalization.csail.mit.edu/) (Models/Projects)

README

        
# Weakly_detector

Tensorflow implementation of "Learning Deep Features for Discriminative Localization"

B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba

Learning Deep Features for Discriminative Localization.

Computer Vision and Pattern Recognition (CVPR), 2016.

[[PDF](http://arxiv.org/pdf/1512.04150.pdf)][[Project Page](http://cnnlocalization.csail.mit.edu/)]

### Results of Caltech256 Dataset

![alt tag](https://github.com/jazzsaxmafia/Weakly_detector/blob/master/results/demo.main.jpg)

### Results of Action40 Dataset

![alt tag](https://github.com/jazzsaxmafia/Weakly_detector/blob/master/results/demo.main2.jpg)

Object localization using only image-level annotation, without bounding box annotation.

* If you want to train the model using custom dataset, you need the pretrained VGG Network weights [[VGG](https://drive.google.com/file/d/0B5o40yxdA9PqOVI5dF9tN3NUc2c/view?usp=sharing)], which is used in [[code](https://github.com/jazzsaxmafia/Weakly_detector/blob/master/src/train.caltech.py#L10)].