4 papers · 1 filter
H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers
Ayushi Mehrotra, Dipkamal Bhusal, Michael Clifford +1
Feature attribution methods explain the predictions of deep neural networks by assigning importance scores to individual input features. However, most existing methods focus solely…
FACE: Faithful Automatic Concept Extraction
Dipkamal Bhusal, Michael Clifford, Sara Rampazzi +1
Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing aut…
Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
Sanish Suwal, Dipkamal Bhusal, Michael Clifford +1
Prior works have shown that neural networks can be heavily pruned while preserving performance, but the impact of pruning on model interpretability remains unclear. In this work, w…
Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning
Sanish Suwal, Shaurya Garg, Dipkamal Bhusal +2
Connected and autonomous vehicles continue to heavily rely on AI systems, where transparency and security are critical for trust and operational safety. Post-hoc explanations provi…