Spatial Attention Noise Masking for Causally Sufficient Interpretability

• URL: http://arxiv.org/abs/2608.14725v1
• Date: Wed, 12 Aug 2026 13:47:30 GMT
• Title: Spatial Attention Noise Masking for Causally Sufficient Interpretability
• Abstract summary: We present a novel approach to interpretability for computer vision models that dynamically masks the input image prior to classification.<n>Most interpretability methods are applied passively to already trained models, which typically result in correlational rather than causal explanations.<n>This work proposes a spatial attention noise masking framework that provides causal explanations about the features sufficient for the prediction.
• Score: 0.21665689529884694
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a novel causal approach to interpretability for computer vision models that dynamically masks the input image prior to classification. The interpretability of deep learning predictions is critical in high-stakes fields such as medical imaging, security, and autonomous driving. Most interpretability methods are applied passively to already trained models, which typically result in correlational rather than causal explanations. Existing causal interpretability methods are limited to post hoc analysis, weakening the causal claims. Additionally, existing active methods generally lack explanations that explicitly assign responsibility to input features. This work proposes a spatial attention noise masking framework that provides causal explanations about the features sufficient for the prediction. The proposed framework consists of: 1) a UNet-style mask generator, and 2) a Resnet18 encoder and linear classifier that classifies both masked and unmasked versions of an input image. The generated masks are regularized to be sparse and spatially smooth, while masked image embeddings are constrained to remain consistent with embeddings from the corresponding unmasked images. The resulting masks can be interpreted as feature attribution maps that are competitive with related interpretability methods while additionally providing strong causal explanations of model predictions. Quantitative evaluations demonstrate mask faithfulness, near-baseline classification performance across five classification tasks despite substantial masking of image information, and robustness to distribution shifts such as background swapping and natural adversarial examples. Qualitative comparisons further demonstrate mask behavior and competitive interpretability relative to state-of-the-art feature attribution methods.

Related papers

• Activation Matching for Explanation Generation [10.850989126934317]
  We generate minimal, faithful explanations for the decision-making of a pretrained classifier on any given image.<n>We train a lightweight autoencoder to output a binary mask $m$ such that the explanation $e = m odot x$ preserves both the model's prediction and the intermediate activations of (x)<n>Our objective combines: (i) multi-layer activation matching with KL divergence to align distributions and cross-entropy to retain the top-1 label for both the image and the explanation.
  arXiv  Detail & Related papers  (2025-09-27T02:12:09Z)
• Evolved Hierarchical Masking for Self-Supervised Learning [49.77271430882176]
  Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training.<n>This paper introduces an evolved hierarchical masking method to pursue general visual cues modeling in self-supervised learning.
  arXiv  Detail & Related papers  (2025-04-12T09:40:14Z)
• Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision [87.15580604023555]
  Unpair-Seg is a novel weakly-supervised open-vocabulary segmentation framework. It learns from unpaired image-mask and image-text pairs, which can be independently and efficiently collected. It achieves 14.6% and 19.5% mIoU on the ADE-847 and PASCAL Context-459 datasets.
  arXiv  Detail & Related papers  (2024-02-14T06:01:44Z)
• Counterfactual Image Generation for adversarially robust and interpretable Classifiers [1.3859669037499769]
  We propose a unified framework leveraging image-to-image translation Generative Adrial Networks (GANs) to produce counterfactual samples. This is achieved by combining the classifier and discriminator into a single model that attributes real images to their respective classes and flags generated images as "fake" We show how the model exhibits improved robustness to adversarial attacks, and we show how the discriminator's "fakeness" value serves as an uncertainty measure of the predictions.
  arXiv  Detail & Related papers  (2023-10-01T18:50:29Z)
• MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask [84.84034179136458]
  A crucial factor leading to the text-image mismatch issue is the inadequate cross-modality relation learning. We propose an adaptive mask, which is conditioned on the attention maps and the prompt embeddings, to dynamically adjust the contribution of each text token to the image features. Our method, termed MaskDiffusion, is training-free and hot-pluggable for popular pre-trained diffusion models.
  arXiv  Detail & Related papers  (2023-09-08T15:53:37Z)
• Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleading [5.124348720450654]
  We show that iterative masking produces large variation in faithfulness scores between otherwise comparable Transformer encoder text classifiers. We explore task-specific considerations that undermine principled comparison of interpretability using iterative masking.
  arXiv  Detail & Related papers  (2023-08-13T15:44:39Z)
• Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training [55.12082817901671]
  We propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT)<n>MaPeT employs autoregressive and permuted predictions to capture intra-patch dependencies.<n>Our results demonstrate that MaPeT achieves competitive performance on ImageNet, compared to baselines and competitors under the same model setting.
  arXiv  Detail & Related papers  (2023-06-12T18:12:19Z)
• Improving Masked Autoencoders by Learning Where to Mask [65.89510231743692]
  Masked image modeling is a promising self-supervised learning method for visual data. We present AutoMAE, a framework that uses Gumbel-Softmax to interlink an adversarially-trained mask generator and a mask-guided image modeling process. In our experiments, AutoMAE is shown to provide effective pretraining models on standard self-supervised benchmarks and downstream tasks.
  arXiv  Detail & Related papers  (2023-03-12T05:28:55Z)
• Towards Improved Input Masking for Convolutional Neural Networks [66.99060157800403]
  We propose a new masking method for CNNs we call layer masking. We show that our method is able to eliminate or minimize the influence of the mask shape or color on the output of the model. We also demonstrate how the shape of the mask may leak information about the class, thus affecting estimates of model reliance on class-relevant features.
  arXiv  Detail & Related papers  (2022-11-26T19:31:49Z)
• Explaining Image Classifiers with Multiscale Directional Image Representation [4.29434097275489]
  We present ShearletX, a novel mask explanation method for image classifiers based on the shearlet transform. To support our method, we propose a mathematical definition for explanation artifacts and an information theoretic score to evaluate the quality of mask explanations.
  arXiv  Detail & Related papers  (2022-11-22T09:24:45Z)
• Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces [12.514483749037998]
  We introduce a novel method to generate causal and yet interpretable counterfactual explanations for image classifiers. We use this framework to obtain contrastive and causal sufficiency and necessity scores as global explanations for black-box classifiers.
  arXiv  Detail & Related papers  (2022-06-10T17:54:46Z)
• What You See is What You Classify: Black Box Attributions [61.998683569022006]
  We train a deep network, the Explainer, to predict attributions for a pre-trained black-box classifier, the Explanandum. Unlike most existing approaches, ours is capable of directly generating very distinct class-specific masks. We show that our attributions are superior to established methods both visually and quantitatively.
  arXiv  Detail & Related papers  (2022-05-23T12:30:04Z)
• Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability [5.387323728379395]
  Saliency maps that identify the most informative regions of an image are valuable for model interpretability. A common approach to creating saliency maps involves generating input masks that mask out portions of an image. We show that a masking model can be trained with as few as 10 examples per class and still generate saliency maps with only a 0.7-point increase in localization error.
  arXiv  Detail & Related papers  (2020-10-19T18:00:36Z)

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.