Bayesian generative models can flag performance loss, bias, and out-of-distribution image content

• URL: http://arxiv.org/abs/2503.17477v1
• Date: Fri, 21 Mar 2025 18:45:28 GMT
• Title: Bayesian generative models can flag performance loss, bias, and out-of-distribution image content
• Authors: Miguel López-Pérez, Marco Miani, Valery Naranjo, Søren Hauberg, Aasa Feragen,
• Abstract summary: Generative models are popular for medical imaging tasks such as anomaly detection, feature extraction, data visualization, or image generation.<n>Since they are parameterized by deep learning models, they are often sensitive to distribution shifts and unreliable when applied to out-of-distribution data.<n>We show how pixel-wise uncertainty can detect out-of-distribution image content such as ink, rulers, and patches.
• Score: 15.835055687646507
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generative models are popular for medical imaging tasks such as anomaly detection, feature extraction, data visualization, or image generation. Since they are parameterized by deep learning models, they are often sensitive to distribution shifts and unreliable when applied to out-of-distribution data, creating a risk of, e.g. underrepresentation bias. This behavior can be flagged using uncertainty quantification methods for generative models, but their availability remains limited. We propose SLUG: A new UQ method for VAEs that combines recent advances in Laplace approximations with stochastic trace estimators to scale gracefully with image dimensionality. We show that our UQ score -- unlike the VAE's encoder variances -- correlates strongly with reconstruction error and racial underrepresentation bias for dermatological images. We also show how pixel-wise uncertainty can detect out-of-distribution image content such as ink, rulers, and patches, which is known to induce learning shortcuts in predictive models.

Related papers

• One-for-More: Continual Diffusion Model for Anomaly Detection [61.12622458367425]
  Anomaly detection methods utilize diffusion models to generate or reconstruct normal samples when given arbitrary anomaly images.<n>Our study found that the diffusion model suffers from severe faithfulness hallucination'' and catastrophic forgetting''<n>We propose a continual diffusion model that uses gradient projection to achieve stable continual learning.
  arXiv  Detail & Related papers  (2025-02-27T07:47:27Z)
• Detecting Discrepancies Between AI-Generated and Natural Images Using Uncertainty [91.64626435585643]
  We propose a novel approach for detecting AI-generated images by leveraging predictive uncertainty to mitigate misuse and associated risks.<n>The motivation arises from the fundamental assumption regarding the distributional discrepancy between natural and AI-generated images.<n>We propose to leverage large-scale pre-trained models to calculate the uncertainty as the score for detecting AI-generated images.
  arXiv  Detail & Related papers  (2024-12-08T11:32:25Z)
• Model Integrity when Unlearning with T2I Diffusion Models [11.321968363411145]
  We propose approximate Machine Unlearning algorithms to reduce the generation of specific types of images, characterized by samples from a forget distribution'' We then propose unlearning algorithms that demonstrate superior effectiveness in preserving model integrity compared to existing baselines.
  arXiv  Detail & Related papers  (2024-11-04T13:15:28Z)
• Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models [72.07462371883501]
  We propose emphProjection Regret (PR), an efficient novelty detection method that mitigates the bias of non-semantic information. PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.
  arXiv  Detail & Related papers  (2023-12-05T09:44:47Z)
• Confidence-Aware and Self-Supervised Image Anomaly Localisation [7.099105239108548]
  We discuss an improved self-supervised single-class training strategy that supports the approximation of probabilistic inference with loosen feature locality constraints. Our method is integrated into several out-of-distribution (OOD) detection models and we show evidence that our method outperforms the state-of-the-art on various benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-23T12:48:47Z)
• Masked Images Are Counterfactual Samples for Robust Fine-tuning [77.82348472169335]
  Fine-tuning deep learning models can lead to a trade-off between in-distribution (ID) performance and out-of-distribution (OOD) robustness. We propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
  arXiv  Detail & Related papers  (2023-03-06T11:51:28Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Fake It Till You Make It: Near-Distribution Novelty Detection by Score-Based Generative Models [54.182955830194445]
  existing models either fail or face a dramatic drop under the so-called near-distribution" setting. We propose to exploit a score-based generative model to produce synthetic near-distribution anomalous data. Our method improves the near-distribution novelty detection by 6% and passes the state-of-the-art by 1% to 5% across nine novelty detection benchmarks.
  arXiv  Detail & Related papers  (2022-05-28T02:02:53Z)
• Robustness via Uncertainty-aware Cycle Consistency [44.34422859532988]
  Unpaired image-to-image translation refers to learning inter-image-domain mapping without corresponding image pairs. Existing methods learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty. We propose a novel probabilistic method based on Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC)
  arXiv  Detail & Related papers  (2021-10-24T15:33:21Z)
• Implicit field learning for unsupervised anomaly detection in medical images [0.8122270502556374]
  An auto-decoder feed-forward neural network learns the distribution of healthy images in the form of a mapping between spatial coordinates and probabilities over a proxy for tissue types. Anomalies are localized using the voxel-wise probability predicted by our model for the restored image. We tested our approach in the task of unsupervised localization of gliomas on brain MR images and compared it to several other VAE-based anomaly detection methods.
  arXiv  Detail & Related papers  (2021-06-09T16:57:22Z)
• Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regression [0.0]
  Probable Variational AutoEncoder (VAE) has become a popular model for anomaly detection in applications such as lesion detection in medical images. We describe an alternative approach that avoids the well-known problem of shrinkage or underestimation of variance. Using estimated quantiles to compute mean and variance under the Gaussian assumption, we compute reconstruction probability as a principled approach to outlier or anomaly detection.
  arXiv  Detail & Related papers  (2020-10-18T17:37:39Z)
• Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations [68.8204255655161]
  Anomaly detection for Magnetic Resonance Images (MRIs) can be solved with unsupervised methods. We have proposed a slice-wise semi-supervised method for tumour detection based on the computation of a dissimilarity function in the latent space of a Variational AutoEncoder. We show that by training the models on higher resolution images and by improving the quality of the reconstructions, we obtain results which are comparable with different baselines.
  arXiv  Detail & Related papers  (2020-07-24T14:02:09Z)
• Overinterpretation reveals image classification model pathologies [15.950659318117694]
  convolutional neural networks (CNNs) on popular benchmarks exhibit troubling pathologies that allow them to display high accuracy even in the absence of semantically salient features. We demonstrate that neural networks trained on CIFAR-10 and ImageNet suffer from overinterpretation. Although these patterns portend potential model fragility in real-world deployment, they are in fact valid statistical patterns of the benchmark that alone suffice to attain high test accuracy.
  arXiv  Detail & Related papers  (2020-03-19T17:12:23Z)

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.