Scaling vision models by depth and parameter count does not consistently improve localisation-based explanation quality across architectures, datasets, and post-hoc methods; smaller models often perform comparably or better.
CLEVR-XAI: A benchmark dataset for the ground truth evaluation of neural network explanations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
A rationale-informed pruning strategy for VLMs yields higher accuracy and more doubly-correct predictions than prior pruning methods on egocentric video benchmarks.
A survey proposing a taxonomy of XAI techniques for food quality research organized by data types and explanation methods.
citing papers explorer
-
Explainable Artificial Intelligence Techniques for Interpretation of Food Models: a Review
A survey proposing a taxonomy of XAI techniques for food quality research organized by data types and explanation methods.