Evaluating Weakly Supervised Object Localization Methods Right? A Study on Heatmap-based XAI and Neural Backed Decision Tree

Erico Tjoa, Cuntai Guan

Keywords: object localization, computer vision, deep learning, deep neural network

TL;DR: Evaluating object localization using XAI methods on MaxBoxAcc metrics. NBDT is tested too as an extension.

Abstract: Choe et al have investigated several aspects of Weakly Supervised Object Localization (WSOL) with only image label. They addressed the ill-posed nature of the problem and showed that WSOL has not significantly improved beyond the baseline method class activation mapping (CAM). We report the results of similar experiments on ResNet50 with some crucial differences: (1) we perform WSOL using heatmap-based eXplanaible AI (XAI) methods (2) our model is not class agnostic since we are interested in the XAI aspect as well. Under similar protocol, we find that XAI methods perform WSOL with very sub-standard MaxBoxAcc scores. The experiment is then repeated for the same model trained with Neural Backed Decision Tree (NBDT) and we found that vanilla CAM yields significantly better WSOL performance after NBDT training.

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: Applications (eg, speech processing, computer vision, NLP)