Skip to yearly menu bar Skip to main content


Poster
in
Affinity Workshop: Tiny Papers Poster Session 3

Evaluating Groups of Features via Consistency, Contiguity, and Stability

Chaehyeon Kim · Weiqiu You · Shreya Havaldar · Eric Wong

Halle B #323
[ ] [ Project Page ]
Wed 8 May 1:45 a.m. PDT — 3:45 a.m. PDT

Abstract:

Feature attributions explain model predictions by assigning importance scores to input features. In high-dimensional data such as images, these scores are often assigned to groups of features at a time. There are a variety of strategies for creating these groups, ranging from simple patches to deep-learning-based segmentation algorithms. What makes certain groups better than others for explanations? We formally define three key criteria for interpretable groups of features: consistency, contiguity, and stability. Surprisingly, we find that patch-based groups outperform groups created via modern segmentation tools.

Chat is not available.