“Studying How to Efficiently and Effectively Guide Models with Explanations” - A Reproducibility Study
Abstract: Model guidance describes the approach of regularizing the explanations of a deep neu-
ral network model towards highlighting the correct features to ensure that the model is
“right for the right reasons”. Rao et al. (2023) conducted an in-depth evaluation of ef-
fective and efficient model guidance for object classification across various loss functions,
attributions methods, models, and ’guidance depths’ to study the effectiveness of differ-
ent methods. Our work aims to (1) reproduce the main results obtained by Rao et al.
(2023), and (2) propose several extensions to their research. We conclude that the major
part of the original work is reproducible, with certain minor exceptions, which we discuss
in this paper. In our extended work, we point to an issue with the Energy Pointing Game
(EPG) metric used for evaluation and propose an extension for increasing its robustness.
In addition, we observe the EPG metric’s predisposition towards favoring larger bounding
boxes, a bias we address by incorporating a corrective penalty term into the original En-
ergy loss function. Furthermore, we revisit the feasibility of using segmentation masks in
light of the original study’s finding that minimal annotated data can significantly boost
model performance. Our findings suggests that Energy loss inherently guides models to
on-object features without the requirement for segmentation masks. Finally, we explore
the role of contextual information in object detection and, contrary to the assumption
that focusing solely on object-specific features suffices for accurate classification, our find-
ings suggest the importance of contextual cues in certain scenarios.
Code available at: https://anonymous.4open.science/r/model_guidance_repro_study.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Camera ready version (de-anonymized, including the link to review page).
Added more details about the experimental setup (App. A) and notation (App. F).
Adjusted the narrative of the human study to better distinguish between OOD and ID scenarios and more clearly define our hypothesis, as well as the conclusion of the study.
Code: https://github.com/ryan-ott/model-guidance-reproducibility
Assigned Action Editor: ~Pablo_Sprechmann1
Submission Number: 2240
Loading