Generative Classifiers Avoid Shortcut Solutions

• URL: http://arxiv.org/abs/2512.25034v1
• Date: Wed, 31 Dec 2025 18:31:46 GMT
• Title: Generative Classifiers Avoid Shortcut Solutions
• Authors: Alexander C. Li, Ananya Kumar, Deepak Pathak,
• Abstract summary: Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail under minor distribution shift.<n>We show that generative classifiers can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones.<n>We find that diffusion-based and autorerimigressive generative classifiers achieve state-of-the-art performance on five standard image and text distribution shift benchmarks.
• Score: 84.23247217037134
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the label. We show that generative classifiers, which use class-conditional generative models, can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones. These generative classifiers are simple to train, avoiding the need for specialized augmentations, strong regularization, extra hyperparameters, or knowledge of the specific spurious correlations to avoid. We find that diffusion-based and autoregressive generative classifiers achieve state-of-the-art performance on five standard image and text distribution shift benchmarks and reduce the impact of spurious correlations in realistic applications, such as medical or satellite datasets. Finally, we carefully analyze a Gaussian toy setting to understand the inductive biases of generative classifiers, as well as the data properties that determine when generative classifiers outperform discriminative ones.

Related papers

• Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective [100.54185280153753]
  We find that both classifier guidance and classifier-free guidance achieve conditional generation by pushing the denoising diffusion trajectories away from decision boundaries.<n>We propose a generic postprocessing step built upon flow-matching to shrink the gap between the learned distribution for a pretrained denoising diffusion model and the real data distribution.
  arXiv  Detail & Related papers  (2025-03-13T17:59:59Z)
• Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation [26.544938760265136]
  Deep neural classifiers rely on spurious correlations between spurious attributes of inputs and targets to make predictions. We propose a self-guided spurious correlation mitigation framework. We show that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori.
  arXiv  Detail & Related papers  (2024-05-06T17:12:21Z)
• Generative Multi-modal Models are Good Class-Incremental Learners [51.5648732517187]
  We propose a novel generative multi-modal model (GMM) framework for class-incremental learning. Our approach directly generates labels for images using an adapted generative model. Under the Few-shot CIL setting, we have improved by at least 14% accuracy over all the current state-of-the-art methods with significantly less forgetting.
  arXiv  Detail & Related papers  (2024-03-27T09:21:07Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Self-supervised GANs with Label Augmentation [43.78253518292111]
  We propose a novel self-supervised GANs framework with label augmentation, i.e., augmenting the GAN labels (real or fake) with the self-supervised pseudo-labels. We demonstrate that the proposed method significantly outperforms competitive baselines on both generative modeling and representation learning.
  arXiv  Detail & Related papers  (2021-06-16T07:58:00Z)
• Towards Robust Classification Model by Counterfactual and Invariant Data Generation [7.488317734152585]
  Spuriousness occurs when some features correlate with labels but are not causal. We propose two data generation processes to reduce spuriousness. Our data generations outperform state-of-the-art methods in accuracy when spurious correlations break.
  arXiv  Detail & Related papers  (2021-06-02T12:48:29Z)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)
• Classify and Generate: Using Classification Latent Space Representations for Image Generations [17.184760662429834]
  We propose a discriminative modeling framework that employs manipulated supervised latent representations to reconstruct and generate new samples belonging to a given class. ReGene has higher classification accuracy than existing conditional generative models while being competitive in terms of FID.
  arXiv  Detail & Related papers  (2020-04-16T09:13:44Z)

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.