https://github.com/iamhankai/attribute-aware-attention
[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning
https://github.com/iamhankai/attribute-aware-attention
attention-mechanism convolutional-neural-networks cub-dataset fine-grained-classification fine-grained-visual-categorization person-reidentification representation-learning
Last synced: 11 months ago
JSON representation
[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning
- Host: GitHub
- URL: https://github.com/iamhankai/attribute-aware-attention
- Owner: iamhankai
- Created: 2018-11-17T08:05:31.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-08-31T14:01:50.000Z (almost 7 years ago)
- Last Synced: 2025-04-06T05:23:40.256Z (about 1 year ago)
- Topics: attention-mechanism, convolutional-neural-networks, cub-dataset, fine-grained-classification, fine-grained-visual-categorization, person-reidentification, representation-learning
- Language: Python
- Homepage: https://arxiv.org/abs/1901.00392
- Size: 661 KB
- Stars: 157
- Watchers: 5
- Forks: 30
- Open Issues: 8
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
## Attribute-Aware Attention Model
Code for ACM Multimedia 2018 oral paper: Attribute-Aware Attention Model for Fine-grained Representation Learning
We have presented results of **fine-grained classification**, **person re-id**, **image retrieval** tasks, including CUB-200-2011, Market-1501, CARS196 datasets in the paper. Here is the example of fine-grained classification. For detailed results, refer to the [original paper](https://dl.acm.org/citation.cfm?id=3240550) or [ArXiv](https://arxiv.org/abs/1901.00392).
### Usage
Requires: Keras 1.2.1 ("image_data_format": "channels_first")
Run in two steps:
1. Download CUB-200-2011 dataset [here](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) and unzip it to `$CUB`; Copy file `tools/processed_attributes.txt` to `$CUB`.
- The `$CUB` dir should be like this:
2. Change `data_dir` in `run.sh` to `$CUB`, run the scprit `sh run.sh` to obtain the result.
- Result on CUB dataset
### Citation
Please use the following bibtex to cite our work:
```
@inproceedings{han2018attribute,
title={Attribute-Aware Attention Model for Fine-grained Representation Learning},
author={Han, Kai and Guo, Jianyuan and Zhang, Chao and Zhu, Mingjian},
booktitle={Proceedings of the 26th ACM international conference on Multimedia},
pages={2040--2048},
year={2018},
organization={ACM}
}
```