Search Results for author:
Found 4 papers, 3 papers with code
ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
Based on the insight that a trained model's classification strategies can be inferred accurately based on explainability heatmaps, we introduce ExMap, an unsupervised two stage mechanism designed to enhance group robustness in traditional classifiers.
Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings
Distance-based classification is frequently used in transductive few-shot learning (FSL).
RC2020 Report: Learning De-biased Representations with Biased Representations
We compare ReBias with other methods - Vanilla, Biased, RUBi (as implemented by the authors), and conclude with a discussion concerning the validity of the claims made by the paper.
A Review and Refinement of Surprise Adequacy
As an adequacy criterion, it has been used to assess the strength of DL test suites.
