← Back to all news
arXiv Machine Learning By Evgenii Kuriabov, David Miller, Jia Li

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

Read the original on arXiv Machine Learning →

arXiv:2607. 06637v1 Announce Type: new Abstract: In this work, we propose a unified approach for diagnosing misclassification and assessing the robustness of black-box classifiers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 9

Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape

arXiv:2403. 06013v2 Announce Type: replace Abstract: This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated.

By Tiejin Chen, Wenwang Huang, Linsey Pang, Dongsheng Luo, Hua Wei
computer-vision
More like this →
arXiv Machine Learning
Sep 23

eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts

The paper introduces eXplaining to Learn (eX2L), an interpretable framework that regularizes a classifier by penalizing similarity between Grad‑CAM maps of the main label classifier and a confounder classifier. This approach decorrelates confounding features from latent representations during training. On the Spawrious Many‑to‑Many Hard Challenge benchmark, eX2L outperforms the current state‑of‑the‑art by 5.49% in average accuracy and 10.90% in worst‑group accuracy, while also demonstrating functional domain invariance through explicit label‑nuisance decoupling.

By Paulo Mario P. Medina, Jose Marie Antonio Mi\~noza, Sebastian C. Iba\~nez
benchmarkssafety
More like this →
arXiv Machine Learning
Jul 10

Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection

arXiv:2603. 23318v2 Announce Type: replace Abstract: Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its prediction.

By Rodrigo F. L. Lassance, Jasper De Bock
More like this →