Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks
Abstract
Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation, but backpropagation techniques are still prevailing because of their computational efficiency. In this work, we combine both approaches as a hybrid visual explanation algorithm and propose an efficient interpretation method for convolutional neural networks. Our method adaptively selects the most critical features that mainly contribute towards a prediction to probe the model by finding the activated features. Experimental results show that the proposed method can reduce the execution time up to 30% while enhancing competitive interpretability without compromising the quality of explanation generated.
Cite
@article{arxiv.2102.07799,
title = {Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks},
author = {Mahesh Sudhakar and Sam Sattarzadeh and Konstantinos N. Plataniotis and Jongseong Jang and Yeonjeong Jeong and Hyunwoo Kim},
journal= {arXiv preprint arXiv:2102.07799},
year = {2021}
}
Comments
5 pages, 4 figures. Accepted in 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021)