mlsanityData to 7 Oct 2026

Does Saliency-Based Training bring Robustness for Deep Neural Networks in Image Classification?

arXiv 2306.16581 ↗First posted 28 Jun 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to highlight the prominent features in the model's output to alleviate this problem, it is still ambiguous if the visually explainable features align with robustness of the model against adversarial examples. In this paper, we investigate the saliency trained model's vulnerability to adversarial examples methods. Models are trained using an online saliency-guided training method and evaluated against popular algorithms of adversarial examples. We quantify the robustness and conclude that despite the well-explained visualizations in the model's output, the salient models suffer from the lower performance against adversarial examples attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

18 of 27 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  8. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  9. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  10. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  11. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  12. 2017Distilling a Neural Network Into a Soft Decision Treecited by 230
6 more
  1. 2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
  2. 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
  3. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  4. 2021Improving Deep Learning Interpretability by Saliency Guided Trainingcited by 68
  5. 2019Saliency Learning: Teaching the Model Where to Pay Attentioncited by 23
  6. 2022Do Explanations Explain? Model Knows Bestcited by 20

Built on by

Not cited yet.