arXiv Machine Learning June 9, 2026 By Tiejin Chen, Wenwang Huang, Linsey Pang, Dongsheng Luo, Hua Wei

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

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

computer-vision

arXiv AI

Aug 3

A Human-Centered Validation of the Explainability-Performance Coefficient

arXiv:2607. 29614v1 Announce Type: cross Abstract: The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI).

By Christian Oliva, Luis F. Lago-Fern\'andez

efficiency

arXiv Machine Learning

Jul 9

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

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.

By Evgenii Kuriabov, David Miller, Jia Li

safety

arXiv AI

Jun 10

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification

arXiv:2411. 05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification.

By Antonio De Santis, Riccardo Campi, Matteo Bianchi, Marco Brambilla

computer-vision benchmarks safety

arXiv Machine Learning

Aug 6

Robustness Emerges Early in Training Dynamics, but Is Not Preserved

arXiv:2608. 04442v1 Announce Type: new Abstract: Robustness to natural corruptions remains a fundamental challenge for deep neural networks.

By Jiangang Yang, Wenhui Shi, Lu Hu, Jing Xing, Jian Liu

computer-vision benchmarks

arXiv AI

1d ago

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

arXiv:2608. 15731v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) deployed in high-risk domains, such as healthcare and autonomous driving, must be not only accurate but also understandable to ensure user trust.

By Haadia Amjad, Ronald Tetzlaff

agents computer-vision robotics safety

arXiv Machine Learning

Jun 16

Enhancing Visual Feature Attribution via Weighted Integrated Gradients

arXiv:2505. 03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential.

By Kien Tran Duc Tuan, Tam Nguyen Trong, Son Nguyen Hoang, Khoat Than, Anh Nguyen Duc

llms computer-vision

Related stories

A Human-Centered Validation of the Explainability-Performance Coefficient

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification

Robustness Emerges Early in Training Dynamics, but Is Not Preserved

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

Enhancing Visual Feature Attribution via Weighted Integrated Gradients