Haohan Wang

icon indicating a website link https://haohanwang.github.io/

icon company University of Illinois Urbana-Champaign icon location Champaign icon location Robust Machine Learning & Computational Biology

Results 7 comments of Haohan Wang

PACS data

Hi, please use the file paths here: https://github.com/HaohanWang/PAR_experiments/tree/master/PACS/filepaths This split follows previous works https://github.com/HaohanWang/HEX_experiments and https://github.com/yogeshbalaji/Meta-Learning-Domain-Generalization/tree/master/data/sourceonly

PACS data

Hi, No, they are not. JigenDG uses yet another split. You might want to read their repo for the details.

PACS data

Hi Zhenlin, sure, but it has been quite a while, I'm not sure I remember everything but I will give you as much information as possible. First of all, we...

PACS data

Yes, we used the weights in the link. I believe only this AlexNet architecture uses conv5. The ResNet in other experiments uses conv2.

PACS data

The previous results are directly from other relevant papers.

PACS data

At line https://github.com/HaohanWang/PAR_experiments/blob/master/PACS/alexNet.py#L322, it looks like I used 1e-5 for art and sketch as the test domain, but something else for the other settings. I checked the git logs, it...

PACS data

Yes, that's the most I can recall. My experiments on 1080Ti. The CIFAR experiments were run and documented by my collaborator though.