search

zkcys001 / UDAStrongBaseline

Open-source stronger baseline for unsupervised or domain adaptive object re-ID.
143 stars 21 forks source link

The result of GLT much lower than paper's #8

Closed woocoder closed 3 years ago

woocoder commented 3 years ago

Hi, I follow the readme to run the GLT code. image And the result mAP is 57.3% in duke->market task (10 iteration), which much lower than paper's 79.5%. image image How can I do to improve the result like paper's? Thanks for your attention.

zkcys001 commented 3 years ago

Thanks for your attention. The result you showed is to use single-time K-means clustering. You can use K-means clustering many times to improve performance. I reproduced the GLT code last several weeks, but it seems to still have some latent bugs, and I will update it recently.

In fact, the DBSCAN can achieve higher performance. I suggest you try to use the stronger baseline or uncertainty model, which are based on DBSCAN~It takes less times than the K-means

In addition, you must use the 4 gpus to train the model.

woocoder commented 3 years ago

Thank you for your reply. I will try it later. Very nice job! Looking forward to the upcoming updates~