Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study

• URL: http://arxiv.org/abs/2602.18502v1
• Date: Tue, 17 Feb 2026 10:51:58 GMT
• Title: Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
• Authors: Sarah Müller, Philipp Berens,
• Abstract summary: Feature disentanglement is a promising approach to mitigate shortcut learning.<n>Shortcut mitigation methods improved classification performance under strong spurious correlations.<n>The best-performing models combine data-centric rebalancing with model-centric disentanglement.
• Score: 6.364545942101905
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although deep learning models in medical imaging often achieve excellent classification performance, they can rely on shortcut learning, exploiting spurious correlations or confounding factors that are not causally related to the target task. This poses risks in clinical settings, where models must generalize across institutions, populations, and acquisition conditions. Feature disentanglement is a promising approach to mitigate shortcut learning by separating task-relevant information from confounder-related features in latent representations. In this study, we systematically evaluated feature disentanglement methods for mitigating shortcuts in medical imaging, including adversarial learning and latent space splitting based on dependence minimization. We assessed classification performance and disentanglement quality using latent space analyses across one artificial and two medical datasets with natural and synthetic confounders. We also examined robustness under varying levels of confounding and compared computational efficiency across methods. We found that shortcut mitigation methods improved classification performance under strong spurious correlations during training. Latent space analyses revealed differences in representation quality not captured by classification metrics, highlighting the strengths and limitations of each method. Model reliance on shortcuts depended on the degree of confounding in the training data. The best-performing models combine data-centric rebalancing with model-centric disentanglement, achieving stronger and more robust shortcut mitigation than rebalancing alone while maintaining similar computational efficiency.

Related papers

• Preventing Shortcut Learning in Medical Image Analysis through Intermediate Layer Knowledge Distillation from Specialist Teachers [0.0]
  Deep learning models are prone to learning shortcuts to problems using spuriously correlated yet irrelevant features of their training data.<n>In high-risk applications such as medical image analysis, this phenomenon may prevent models from using clinically meaningful features when making predictions.<n>We propose a novel knowledge distillation framework that leverages a teacher network fine-tuned on a small subset of task-relevant data to mitigate shortcut learning.
  arXiv  Detail & Related papers  (2025-11-21T17:18:35Z)
• Iterative Misclassification Error Training (IMET): An Optimized Neural Network Training Technique for Image Classification [0.5115559623386964]
  We introduce Iterative Misclassification Error Training (IMET), a novel framework inspired by curriculum learning and coreset selection.<n>IMET aims to identify misclassified samples in order to streamline the training process, while prioritizing the model's attention to edge case senarious and rare outcomes.<n>The paper evaluates IMET's performance on benchmark medical image classification datasets against state-of-the-art ResNet architectures.
  arXiv  Detail & Related papers  (2025-07-01T04:14:16Z)
• Sub-Clustering for Class Distance Recalculation in Long-Tailed Drug Classification [3.015770349327888]
  In the field of drug chemistry, certain tail classes exhibit higher identifiability during training due to their unique molecular structural features.<n>We propose a novel method that breaks away from the traditional static evaluation paradigm based on sample size.
  arXiv  Detail & Related papers  (2025-04-07T00:09:10Z)
• Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification [8.975676404678374]
  We present a strategy for improving the performance and generalization capabilities of models trained in low-data regimes. The proposed method starts with a pre-training phase, where features learned in a self-supervised learning setting are disentangled to improve the robustness of the representations for downstream tasks. We then introduce a meta-fine-tuning step, leveraging related classes between meta-training and meta-testing phases but varying the level.
  arXiv  Detail & Related papers  (2024-03-26T09:36:20Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• A Discrepancy Aware Framework for Robust Anomaly Detection [51.710249807397695]
  We present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies. Our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance.
  arXiv  Detail & Related papers  (2023-10-11T15:21:40Z)
• Learning with Noisy Labels through Learnable Weighting and Centroid Similarity [5.187216033152917]
  noisy labels are prevalent in domains such as medical diagnosis and autonomous driving. We introduce a novel method for training machine learning models in the presence of noisy labels. Our results show that our method consistently outperforms the existing state-of-the-art techniques.
  arXiv  Detail & Related papers  (2023-03-16T16:43:24Z)
• On Modality Bias Recognition and Reduction [70.69194431713825]
  We study the modality bias problem in the context of multi-modal classification. We propose a plug-and-play loss function method, whereby the feature space for each label is adaptively learned. Our method yields remarkable performance improvements compared with the baselines.
  arXiv  Detail & Related papers  (2022-02-25T13:47:09Z)
• Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
  We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
  arXiv  Detail & Related papers  (2020-06-12T12:23:50Z)
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [71.80319052891817]
  We present a relation-driven semi-supervised framework for medical image classification. It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
  arXiv  Detail & Related papers  (2020-05-15T06:57:54Z)

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.