Discovery and Spatial Characterisation of Multiple Shortcut Groups for Auditing Vision Model Bias

• URL: http://arxiv.org/abs/2608.14051v1
• Date: Fri, 14 Aug 2026 07:57:38 GMT
• Title: Discovery and Spatial Characterisation of Multiple Shortcut Groups for Auditing Vision Model Bias
• Abstract summary: We group per-image shortcut and task contribution maps into recurring spatial patterns using K-means and non-negative matrix factorisation.<n>Across CelebA, CheXpert, Waterbirds, Camelyon17, and ISIC 2019, and across ResNet and ViT models, the discovered shortcut groups reveal both shared and distinct spatial patterns of shortcut and task contribution.
• Score: 38.183226610951806
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning models trained on datasets with spurious correlations can achieve high average accuracy whilst relying on shortcut features that do not generalise out of distribution. Whilst out-of-distribution testing highlights subgroup performance disparities arising from shortcut learning, it does not localise the regions within images that are associated with it. Existing research mostly uses attribution maps from interpretability methods to understand the spatial nature of spurious correlations. For example, conditional alignment methods separate task-relevant evidence from evidence tied to spurious correlations by comparing attribution maps from a task model, a sensitive attribute model, and a bias-reduced reference model. This yields shortcut-aligned and task-aligned contribution maps for each image. However, existing methods aggregate these maps across the dataset, potentially masking recurring spatial shortcut patterns that occur only in subsets of images. We address this limitation by grouping per-image shortcut and task contribution maps into recurring spatial patterns using K-means and non-negative matrix factorisation, and visualising the resulting shortcut groups through contribution maps and representative examples. Across CelebA, CheXpert, Waterbirds, Camelyon17, and ISIC2019, and across ResNet and ViT models, the discovered shortcut groups reveal both shared and distinct spatial patterns of shortcut and task contribution, with varying subgroup composition and error rates, enabling targeted inspection of image subsets with higher error rates. We perform input occlusion and internal test-time interventions to show that masking or suppressing task contribution regions substantially degrades the model classification performance and propose a combined shortcut suppression and task amplification feature intervention approach which generally reduces performance disparities.

Related papers

• H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers [2.7415651415305597]
  We introduce H-Sets, a novel framework for discovering and attributing higher-order feature interactions in image classifiers.<n>We attribute each set with IDG-Vis, a set-level extension of Integrated Directional Gradients that integrates directional gradients along pixel-space paths.<n> Evaluations across VGG, ResNet, DenseNet and MobileNet models on ImageNet and CUB datasets show that H-Sets generate more interpretable and faithful saliency maps.
  arXiv  Detail & Related papers  (2026-04-23T20:03:17Z)
• Few-Shot Pattern Detection via Template Matching and Regression [52.79291493477272]
  We propose a simple yet effective detector based on template matching and regression, dubbed TMR.<n>It effectively preserves and leverages the spatial layout of exemplars through a minimalistic structure with a small number of learnable convolutional or projection layers on top of a frozen backbone.<n>Our method outperforms the state-of-the-art methods on the three benchmarks, RPINE, FSCD-147, and FSCD-LVIS, and demonstrates strong generalization in cross-dataset evaluation.
  arXiv  Detail & Related papers  (2025-08-25T03:52:42Z)
• Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification [0.0]
  Deep learning dominates image classification tasks, yet understanding how models arrive at predictions remains a challenge.<n>Much research focuses on local explanations of individual predictions, such as saliency maps, which visualise the influence of specific pixels on a model's prediction.<n>We propose Segment Attribution Tables (SATs), a method for summarising local saliency explanations into (semi-)global insights.
  arXiv  Detail & Related papers  (2025-06-29T14:11:02Z)
• NubbleDrop: A Simple Way to Improve Matching Strategy for Prompted One-Shot Segmentation [2.2559617939136505]
  We propose a simple and training-free method to enhance the validity and robustness of the matching strategy. The core concept involves randomly dropping feature channels (setting them to zero) during the matching process. This technique mimics discarding pathological nubbles, and it can be seamlessly applied to other similarity computing scenarios.
  arXiv  Detail & Related papers  (2024-05-19T08:00:38Z)
• Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation [79.05949524349005]
  We propose AuxSegNet+, a weakly supervised auxiliary learning framework to explore the rich information from saliency maps. We also propose a cross-task affinity learning mechanism to learn pixel-level affinities from the saliency and segmentation feature maps.
  arXiv  Detail & Related papers  (2024-03-02T10:03:21Z)
• Common-Sense Bias Modeling for Classification Tasks [15.683471433842492]
  We propose a novel framework to extract comprehensive biases in image datasets based on textual descriptions.<n>Our method uncovers novel model biases in multiple image benchmark datasets.<n>The discovered bias can be mitigated by simple data re-weighting to de-correlate the features.
  arXiv  Detail & Related papers  (2024-01-24T03:56:07Z)
• EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models [52.3015009878545]
  We develop an image segmentor capable of generating fine-grained segmentation maps without any additional training. Our framework identifies semantic correspondences between image pixels and spatial locations of low-dimensional feature maps. In extensive experiments, the produced segmentation maps are demonstrated to be well delineated and capture detailed parts of the images.
  arXiv  Detail & Related papers  (2024-01-22T07:34:06Z)
• Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection [15.212031255539022]
  Anomaly detection (AD) is a fundamental task in computer vision. We propose CutSwap, which leverages saliency guidance to incorporate semantic cues for augmentation. CutSwap achieves state-of-the-art AD performance on two mainstream AD benchmark datasets.
  arXiv  Detail & Related papers  (2023-11-30T08:03:53Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.