Papers › Attributional Robustness Training using Input-Gradient Spatial Alignment

Attributional Robustness Training using Input-Gradient Spatial Alignment

29 Nov 2019ECCV 2020 8arXiv:1911.13073archive 2025-07-28

Mayank Singh, Nupur Kumari, Puneet Mangla, Abhishek Sinha, Vineeth N. Balasubramanian, Balaji Krishnamurthy

Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the explanations could be manipulated easily by adding visually imperceptible perturbations to the input while keeping the model's prediction intact. In this work, we study the problem of attributional robustness (i.e. models having robust explanations) by showing an upper bound for attributional vulnerability in terms of spatial correlation between the input image and its explanation map. We propose a training methodology that learns robust features by minimizing this upper bound using soft-margin triplet loss. Our methodology of robust attribution training (\textit{ART}) achieves the new state-of-the-art attributional robustness measure by a margin of ≈ 6-18 % on several standard datasets, ie. SVHN, CIFAR-10 and GTSRB. We further show the utility of the proposed robust training technique (\textit{ART}) in the downstream task of weakly supervised object localization by achieving the new state-of-the-art performance on CUB-200 dataset.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

nupurkmr9/Attributional-Robustness officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BIG-bench Machine LearningObject LocalizationWeakly-Supervised Object Localization

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly-Supervised Object Localization CUB-200-2011 ART Top-1 Error Rate 34.8 #9 of 10 Archive leaderboard report
Weakly-Supervised Object Localization CUB-200-2011 ART Top-1 Localization Accuracy 65.22 #9 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections