I'm on my way to #NeurIPS2024. On Friday I'm going to present my latest paper with Yuval Benjamini. The gist is in the comments, and come chat with me to hear more!
Comments
Log in with your Bluesky account to leave a comment
But in zero-shot, we face new classes at test time. To adapt, we need to know which "kind" of classes to emphasize. But in reality, the shift is often unknown.
In this paper, we tackle shifts caused by an unknown attribute with an approach opposite to bootstrapping: we use small samples to generate synthetic environments with different "kinds" of classes and learn more robust data representations.
Comments
East Exhibit Hall A-C #2204