Domain Generalisation Next Steps #460
Unanswered
RohitSingh1226
asked this question in
Q&A
Replies: 3 comments
-
我已经收到您的邮件,会尽快处理。
|
Beta Was this translation helpful? Give feedback.
0 replies
-
你好,这是贺雯丽的自动回复,您的信息已经收到。祝身体健康,万事如意! 贺雯丽
|
Beta Was this translation helpful? Give feedback.
0 replies
-
Any update? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello all,
I have a custom dataset with two-three environments, I have setup the benchmark on the DomainBed (https://github.com/facebookresearch/DomainBed?tab=readme-ov-file. I have tried a variety of algorithm and networks, I have understood the relationship between the data and the domains. This has helped me boost the results but not too significantly. I am also not running the sweep just yet until I experiment on some model-agnostic methods to improve the models generalisation capabilities. Using LLM foundation models is also not in my scope since we want to keep the model size low with low computational cost. Does anyone have any ideas that might help me?
Thanks for your time
Beta Was this translation helpful? Give feedback.
All reactions