Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing

• URL: http://arxiv.org/abs/2603.07302v1
• Date: Sat, 07 Mar 2026 18:00:05 GMT
• Title: Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing
• Abstract summary: We propose a lightweight feature-map smoothing block that applies a differentiable Gaussian filter in an intermediate layer.<n>Across FMNIST, CIFAR-10, and ImageNette, our method preserves the sparsity benefits of adversarial training while improving both input-side stability and output-side stability.
• Score: 4.014524824655106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in high-stakes settings. Most prior work improves explanations by modifying the attribution algorithm, leaving open how the training procedure shapes explanation quality. We take a training-centered view and first provide a curvature-based analysis linking attribution stability to how smoothly the input-gradient field varies locally. Guided by this connection, we study adversarial training and identify a consistent trade-off: it yields sparser and more input-stable saliency maps, but can degrade output-side stability, causing explanations to change even when predictions remain unchanged and logits vary only slightly. To mitigate this, we propose augmenting adversarial training with a lightweight feature-map smoothing block that applies a differentiable Gaussian filter in an intermediate layer. Across FMNIST, CIFAR-10, and ImageNette, our method preserves the sparsity benefits of adversarial training while improving both input-side stability and output-side stability. A human study with 65 participants further shows that smoothed adversarial saliency maps are perceived as more sufficient and trustworthy. Overall, our results demonstrate that explanation quality is critically shaped by training, and that simple smoothing with robust training provides a practical path toward saliency maps that are both sparse and stable.

Related papers

• Selectivity Drives Efficiency: Dataset Pruning for Visual Place Recognition [52.52131290631774]
  We propose a place-wise dataset pruning framework tailored for visual place recognition (VPR)<n>Our method treats each place as the basic pruning unit and introduces two novel metrics, i.e., intra-place diversity (IPD) and inter-place similarity (IPS)<n>Experiments demonstrate that our method consistently outperforms state-of-the-art DP baselines under different pruning ratios.
  arXiv  Detail & Related papers  (2026-07-16T12:16:00Z)
• SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation [4.096797783087454]
  SaliencyDecor is a training framework that enforces feature decorrelation to improve attribution fidelity without modifying saliency methods or model architectures.<n>We show that our method produces substantially sharper and more object-focused saliency maps while simultaneously improving predictive performance.
  arXiv  Detail & Related papers  (2026-04-28T07:25:07Z)
• Learn to Rank: Visual Attribution by Learning Importance Ranking [58.69028273772474]
  We propose a new approach to generate visual attribution maps for computer vision models.<n>Our method produces dense, pixel-level attributions in a single forward pass with optional, few-step gradient refinement.<n>Our experiments demonstrate consistent quantitative improvements and sharper, boundary-aligned explanations.
  arXiv  Detail & Related papers  (2026-04-07T12:53:22Z)
• Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability [9.054540533394926]
  Saliency maps have been widely used to interpret the decisions of neural network classifiers.<n>Standard-based maps are frequently observed to be highly sensitive to the randomness of training data and the gradientity in the training process.<n>We study the role of Gaussian smoothing in the well-known Smooth-Grad algorithm in the stability of the gradient-based maps to the randomness of training samples.
  arXiv  Detail & Related papers  (2024-11-06T13:26:57Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• A Learning Paradigm for Interpretable Gradients [9.074325843851726]
  We present a novel training approach to improve the quality of gradients for interpretability. We find that the resulting gradient is qualitatively less noisy and improves quantitatively the interpretability properties of different networks.
  arXiv  Detail & Related papers  (2024-04-23T13:32:29Z)
• Confidence-aware Training of Smoothed Classifiers for Certified Robustness [75.95332266383417]
  We use "accuracy under Gaussian noise" as an easy-to-compute proxy of adversarial robustness for an input. Our experiments show that the proposed method consistently exhibits improved certified robustness upon state-of-the-art training methods.
  arXiv  Detail & Related papers  (2022-12-18T03:57:12Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations [54.23691425062034]
  We study the continuous-time dynamics induced by GAN training. From this perspective, we hypothesise that instabilities in training GANs arise from the integration error. We experimentally verify that well-known ODE solvers (such as Runge-Kutta) can stabilise training.
  arXiv  Detail & Related papers  (2020-10-28T15:23:49Z)
• On Saliency Maps and Adversarial Robustness [22.75851089729379]
  Saliency based Adversarial training (SAT) to use saliency maps to improve adversarial robustness of a model. We show how using finer and stronger saliency maps leads to more robust models.
  arXiv  Detail & Related papers  (2020-06-14T07:41:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.