Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

• URL: http://arxiv.org/abs/2607.12464v1
• Date: Tue, 14 Jul 2026 07:45:46 GMT
• Title: Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification
• Abstract summary: Class-Contrastive Influence (C2I) is a criterion that quantifies a sample's usefulness through its gradient-based influence on the classifier.<n>We show that high-C2I samples are hard, boundary-proximal examples that help refine the decision boundary and improve robustness.
• Score: 15.393927572527828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task. Existing approaches largely improve synthetic data by increasing realism, diversity, or domain adaptation, while overlooking a more fundamental question: how should sample usefulness for classification be measured and optimized? We address this with Class-Contrastive Influence (C2I), a criterion that quantifies a sample's usefulness through its gradient-based influence on the classifier. We find that effective samples exhibit a strong C2I gap: their loss gradients align with validation gradients from the same class and oppose those from other classes. Our analysis further suggests that such high-C2I samples are hard, boundary-proximal examples that help refine the decision boundary and improve robustness. Building on this insight, we fine-tune diffusion models with reinforcement learning using a C2I-based reward to steer generation toward class-informative samples. Across several few-shot medical imaging benchmarks, C2I-guided generation improves downstream accuracy and robustness over diffusion-based augmentation baselines, showing that synthetic augmentation is most effective when guided by task usefulness rather than image quality alone.

Related papers

• Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks [36.94429692322632]
  Class imbalance is a persistent challenge in visual recognition.<n>We propose a lightweight synthetic data augmentation pipeline that fine-tunes a LoRA adapter on as few as 20-50 real images of a rare class.
  arXiv  Detail & Related papers  (2026-05-12T10:11:57Z)
• Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions [6.219934229461855]
  Long-tailed distributions class are pervasive in multi-class medical datasets.<n>This limitation is particularly problematic in medical applications, where rare classes often correspond to severe or high-risk diseases.<n>We introduce a diffusion-model-driven synthetic data augmentation pipeline tailored for medical long-tailed classification.
  arXiv  Detail & Related papers  (2026-05-04T23:18:22Z)
• Cough Classification using Few-Shot Learning [0.7136933021609079]
  We leverage Prototypical Networks with spectrogram representations of cough sounds to address the challenge of limited labeled data.<n>Our study evaluates whether few-shot learning can enable models to achieve performance comparable to traditional deep learning approaches.<n> Experimental findings show that few-shot learning models can achieve competitive accuracy.
  arXiv  Detail & Related papers  (2025-09-11T14:56:47Z)
• Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free [0.7624308578421438]
  This work presents the first exploration of the potential of class conditional diffusion models for 2D medical image classification.<n>We develop a novel majority voting scheme shown to improve the performance of medical diffusion classifiers.<n>Experiments on the CheXpert and ISIC Melanoma skin cancer datasets demonstrate that foundation and trained-from-scratch diffusion models achieve competitive performance.
  arXiv  Detail & Related papers  (2025-02-06T00:37:21Z)
• Understanding the Detrimental Class-level Effects of Data Augmentation [63.1733767714073]
  achieving optimal average accuracy comes at the cost of significantly hurting individual class accuracy by as much as 20% on ImageNet. We present a framework for understanding how DA interacts with class-level learning dynamics. We show that simple class-conditional augmentation strategies improve performance on the negatively affected classes.
  arXiv  Detail & Related papers  (2023-12-07T18:37:43Z)
• Synthetic Augmentation with Large-scale Unconditional Pre-training [4.162192894410251]
  We propose a synthetic augmentation method called HistoDiffusion to reduce the dependency on annotated data. HistoDiffusion can be pre-trained on large-scale unlabeled datasets and later applied to a small-scale labeled dataset for augmented training. We evaluate our proposed method by pre-training on three histopathology datasets and testing on a histopathology dataset of colorectal cancer (CRC) excluded from the pre-training datasets.
  arXiv  Detail & Related papers  (2023-08-08T03:34:04Z)
• Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
  We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification. Our generative approach to classification attains strong results on a variety of benchmarks. Our results are a step toward using generative over discriminative models for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T17:59:56Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation [72.58308581812149]
  We propose an effective approach, dubbed SelectAugment, to select samples to be augmented in a deterministic and online manner. Specifically, in each batch, we first determine the augmentation ratio, and then decide whether to augment each training sample under this ratio. In this way, the negative effects of the randomness in selecting samples to augment can be effectively alleviated and the effectiveness of DA is improved.
  arXiv  Detail & Related papers  (2021-12-06T08:38:38Z)
• Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation [64.59521853145368]
  Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event. To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites. This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features.
  arXiv  Detail & Related papers  (2021-09-08T07:56:51Z)
• Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification [75.27973258196934]
  We propose a novel Categorical Relation-preserving Contrastive Knowledge Distillation (CRCKD) algorithm, which takes the commonly used mean-teacher model as the supervisor. With this regularization, the feature distribution of the student model shows higher intra-class similarity and inter-class variance. With the contribution of the CCD and CRP, our CRCKD algorithm can distill the relational knowledge more comprehensively.
  arXiv  Detail & Related papers  (2021-07-07T13:56:38Z)

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.