/DSAH

[CIKM2022] Deep Self-Adaptive Hashing for Image Retrieval

Primary LanguagePython

DSAH

This is the official Tensorflow implementation for our CIKM'22 paper Deep Self-Adaptive Hashing for Image Retrieval.

DSAH

Preparation

  1. Install dependencies
conda create -n dsah python=3.6
source activate dsah
pip install -r requirements.txt
  1. Download the VGG pretrained weights from here.
  2. Download the pre-extracted features, RGB data for CIFAR-10, FLICKR25K and NUS-WIDE datasets.
  3. Create an initial similarity matrix based on W_create.py for each datasets.

Training & Eval

  1. Run train_cifar_gpu.sh or run_cifar_gpu.py to train the hash model, which will save the hash code during training.
  2. Run eval.py to evaluate the retrieval performance of saved hash code.

Citation

If you find our work helps, please cite our paper.

@inproceedings{lin2021deep,
  title={Deep Self-Adaptive Hashing for Image Retrieval},
  author={Lin, Qinghong and Chen, Xiaojun and Zhang, Qin and Tian, Shangxuan and Chen, Yudong},
  booktitle={Proceedings of the 30th ACM International Conference on Information \& Knowledge Management},
  pages={1028--1037},
  year={2021}
}