Search Results for author:
Found 2 papers, 0 papers with code
Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
Vision-language models, such as CLIP, have shown promising Out-of-Distribution (OoD) generalization under various types of distribution shifts.
Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
A promising solution to this problem is last-layer retraining, which involves retraining the linear classifier head on a small subset of data without spurious cues.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
