[ACM MM 2023] Self-Distillation Dual-Memory Online Hashing with Hash Centers for Streaming Data Retrieval

Official matlab implementation of SDOH-HC, from the following paper:

Self-Distillation Dual-Memory Online Hashing with Hash Centers for Streaming Data Retrieval
Chong-Yu Zhang, Xin Luo, Yu-Wei Zhan, Peng-Fei Zhang, Zhen-Duo Chen, Yongxin Wang, Xun Yang, and Xin-Shun Xu.

Highlights

Running Environment

Matlab

Datasets

We use three datasets to perform our experiments, i.e., CIFAR-10, MIRFLICKR-25K, and NUS-WIDE.
You can download all dataset from HERE.

Run demo

Run mymain.m.

mymain

Some important files:

mymain.m: main program.
train_twostep.m: function to compute the hash code and hash function of training data.
mAP.m : function to compute the mAP of hashing method.
Kernelize.m: function to transform the original features to kernel features.

Citation

If you find our work is useful for your research, please consider citing:

@inProceedings{zhang2023self,
author = {Zhang, Chong-Yu and Luo, Xin and Zhan, Yu-Wei and Zhang, Peng-Fei and Chen, Zhen-Duo and Wang Yongxin and Yang, Xun and Xu, Xin-Shun},
title = {Self-distillation dual-memory online hashing with hash centers for streaming data retrieval},
booktitle = {Proceedings of the 31st ACM International Conference on Multimedia},
pages={6340--6349},
year = {2023}
}

Contact

If you have any questions, feel free to contact us.

Stars

Stargazers