Self-Improving Diffusion Classifiers with Minority Preference Optimization

• URL: http://arxiv.org/abs/2607.03770v1
• Date: Sat, 04 Jul 2026 08:42:08 GMT
• Title: Self-Improving Diffusion Classifiers with Minority Preference Optimization
• Abstract summary: We show a direct relationship between minority sampling in generation and the perception capability of diffusion classifiers.<n>We propose textitSelf-Improving Diffusions with Minority Preference Optimization (MiPO), which fine-tunes a pretrained diffusion model using minority preference rewards.
• Score: 16.52248070887429
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance. However, their effectiveness is strongly tied to the pretraining data distribution: they perform well in majority, high-density regions of the data manifold, but are significantly less accurate in minority, low-density regions. Although prior works on minority sampling have focused on generating more minority-like images, what minority sampling fundamentally enables beyond generation remains underexplored. In this paper, we reveal a direct relationship between minority sampling in generation and the perception capability of diffusion classifiers. Specifically, we show that enhancing minority sampling broadens the coverage of underrepresented regions on the data manifold, thereby improving diffusion-based recognition. To exploit this connection, we propose \textit{Self-Improving Diffusion Classifiers with Minority Preference Optimization} (MiPO), which fine-tunes a pretrained diffusion model using minority preference rewards. Using only arbitrary caption data, MiPO generates candidate samples, rewards those that better cover minority regions, and optimizes the model with LoRA and Group Relative Policy Optimization, without additional image data, external foundation models, or external reward models. This enables stable, prompt-adaptive minority sampling and translates low-density generative coverage into improved zero-shot diffusion classification. To sum up, we show that diffusion classifier perception is biased toward majority regions, demonstrate that this bias can be alleviated through minority preference optimization, and evaluate MiPO on five standard datasets.

Related papers

• When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO [66.10041557056562]
  This paper explores the role of preference data in the training process of diffusion models.<n>We propose Adaptive-DPO -- a novel approach that incorporates a minority-instance-aware metric into the DPO objective.<n>Our experiments demonstrate that this method effectively handles both synthetic minority data and real-world preference data.
  arXiv  Detail & Related papers  (2025-03-21T07:33:44Z)
• Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation [57.19995625893062]
  Minority samples are underrepresented instances located in low-density regions of a data manifold.<n>We present a simple yet powerful guidance-free approach called Boost-and-Skip for generating minority samples.<n>We highlight that these seemingly-trivial modifications are supported by solid theoretical and empirical evidence.
  arXiv  Detail & Related papers  (2025-02-10T14:37:26Z)
• Self-Guided Generation of Minority Samples Using Diffusion Models [57.319845580050924]
  We present a novel approach for generating minority samples that live on low-density regions of a data manifold. Our framework is built upon diffusion models, leveraging the principle of guided sampling. Experiments on benchmark real datasets demonstrate that our approach can greatly improve the capability of creating realistic low-likelihood minority instances.
  arXiv  Detail & Related papers  (2024-07-16T10:03:29Z)
• Generative Oversampling for Imbalanced Data via Majority-Guided VAE [15.93867386081279]
  We propose a novel over-sampling model, called Majority-Guided VAE(MGVAE), which generates new minority samples under the guidance of a majority-based prior. In this way, the newly generated minority samples can inherit the diversity and richness of the majority ones, thus mitigating overfitting in downstream tasks.
  arXiv  Detail & Related papers  (2023-02-14T06:35:23Z)
• Don't Play Favorites: Minority Guidance for Diffusion Models [59.75996752040651]
  We present a novel framework that can make the generation process of the diffusion models focus on the minority samples. We develop minority guidance, a sampling technique that can guide the generation process toward regions with desired likelihood levels.
  arXiv  Detail & Related papers  (2023-01-29T03:08:47Z)
• Proposal Distribution Calibration for Few-Shot Object Detection [65.19808035019031]
  In few-shot object detection (FSOD), the two-step training paradigm is widely adopted to mitigate the severe sample imbalance. Unfortunately, the extreme data scarcity aggravates the proposal distribution bias, hindering the RoI head from evolving toward novel classes. We introduce a simple yet effective proposal distribution calibration (PDC) approach to neatly enhance the localization and classification abilities of the RoI head.
  arXiv  Detail & Related papers  (2022-12-15T05:09:11Z)
• Counterfactual-based minority oversampling for imbalanced classification [11.140929092818235]
  A key challenge of oversampling in imbalanced classification is that the generation of new minority samples often neglects the usage of majority classes. We present a new oversampling framework based on the counterfactual theory.
  arXiv  Detail & Related papers  (2020-08-21T14:13:15Z)
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models [101.67587566218928]
  We formalize the problem of minority inclusion as one of data coverage. We then propose to improve data coverage by harmonizing adversarial training with reconstructive generation. We develop an extension that allows explicit control over the minority subgroups that the model should ensure to include.
  arXiv  Detail & Related papers  (2020-04-07T13:31:33Z)

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.