Search Results for author:
Found 3 papers, 3 papers with code
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
However, we highlight an inherent limitation in these projection-based CIR: a task discrepancy of text encoders between the original pre-training task of the encoders (text $\leftrightarrow$ image) and the target CIR task (image + text $\leftrightarrow$ image), which potentially negatively impacts CIR performance.
TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers
In addition, we propose a systematic validation procedure that checks whether the generated words are compatible with the embedding space of CLIP and the image classifier, which is shown to be effective for improving debiasing performance.
Towards More Robust Interpretation via Local Gradient Alignment
However, the lack of considering the normalization of the attributions, which is essential in their visualizations, has been an obstacle to understanding and improving the robustness of feature attribution methods.
