Year: 2026
Type: article
Abstract: Saliency methods are widely used to visualize which input features are deemed relevant to a model’s prediction. However, their visual plausibility can obscure critical limitations. In this work, we propose a diagnostic test for class sensitivity: a method’s ability to distinguish between competing class labels on the same input. Through experiments on single-label natural-image classification, we show that many widely used saliency methods produce nearly identical explanations regardless of the class label, calling into question their reliability. We find that class-insensitive behavior persists across multiple convolutional architectures and datasets, suggesting that the failure mode is not tied to a single model family or benchmark. Motivated by these findings, we introduce CASE, a contrastive explanation method that isolates features for the predicted class. We evaluate CASE using the proposed diagnostic and a perturbation-based fidelity test, and show that it produces consistently more class-specific explanations while maintaining competitive fidelity.
Source: Machine Learning
Authors: Dane Williamson, Yangfeng Ji, Matthew Dwyer
Institution: University of Virginia
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,290
Funder: National Science Foundation
OpenAlex ID: W4417129333
FWCI:
Cites:
Cited by:
Related to: