The effectiveness of feature attribution methods and its correlation with automatic evaluation scores

Giang Nguyen, Daeyoung Kim, Anh Nguyen

Keywords: feature attribution, nearest neighbors, image classification, imagenet, stanford dog, user-study

Abstract:

Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications.
Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these tools in their work.
However, despite humans being the target end-users, most attribution methods were only evaluated on proxy automatic-evaluation metrics (Zhang et al. 2018; Zhou et al. 2016; Petsiuk et al. 2018). In this paper, we conduct the first user study to measure attribution map effectiveness in assisting humans in ImageNet classification and Stanford Dogs fine-grained classification, and when an image is natural or adversarial (i.e., contains adversarial perturbations). Overall, feature attribution is surprisingly not more effective than showing humans nearest training-set examples. On a harder task of fine-grained dog categorization, presenting attribution maps to humans does not help, but instead hurts the performance of human-AI teams compared to AI alone. Importantly, we found automatic attribution-map evaluation measures to correlate poorly with the actual human-AI team performance. Our findings encourage the community to rigorously test their methods on the downstream human-in-the-loop applications and to rethink the existing evaluation metrics.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/anguyen8/effectiveness-attribution-maps