Examining the Difference Among Transformers and CNNs with Explanation Methods

Mingqi Jiang, Saeed Khorram, Li Fuxin

Keywords: Explanation, transformers, multiple explanations

Abstract: We propose a methodology that systematically applies deep explanation algorithms on a dataset-wide basis, to compare different types of visual recognition backbones, such as convolutional networks (CNNs), global attention networks, and local attention networks. We examine both qualitative visualizations and quantitative statistics across the dataset, in order to generate intuitions that are not just anecdotal, but are supported by the statistics computed on the whole dataset. Specifically, we propose two methods. The first one, sub-explanation counting, systematically searches for minimally-sufficient explanations of all images and count the amount of sub-explanations for each network. The second one, called cross-testing, computes salient regions using one network and then evaluates the performance by only showing these regions as an image to other networks. Through a combination of qualitative insights and quantitative statistics, we illustrate that 1) there are significant differences between the salient features of CNNs and attention models; 2) the occlusion-robustness in local attention models and global attention models may come from different decision-making mechanisms.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)