Diffuse and Disperse: Image Generation with Representation Regularization

• URL: http://arxiv.org/abs/2506.09027v2
• Date: Thu, 24 Jul 2025 15:55:00 GMT
• Title: Diffuse and Disperse: Image Generation with Representation Regularization
• Authors: Runqian Wang, Kaiming He,
• Abstract summary: We propose textitDispersive Loss, a plug-and-play regularizer that effectively improves diffusion-based generative models.<n>Our loss function encourages internal representations to disperse in the hidden space, analogous to contrastive self-supervised learning.<n>Compared to the recent method of representation alignment (REPA), our approach is self-contained and minimalist, requiring no pre-training, no additional parameters, and no external data.
• Score: 23.413550999126173
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The development of diffusion-based generative models over the past decade has largely proceeded independently of progress in representation learning. These diffusion models typically rely on regression-based objectives and generally lack explicit regularization. In this work, we propose \textit{Dispersive Loss}, a simple plug-and-play regularizer that effectively improves diffusion-based generative models. Our loss function encourages internal representations to disperse in the hidden space, analogous to contrastive self-supervised learning, with the key distinction that it requires no positive sample pairs and therefore does not interfere with the sampling process used for regression. Compared to the recent method of representation alignment (REPA), our approach is self-contained and minimalist, requiring no pre-training, no additional parameters, and no external data. We evaluate Dispersive Loss on the ImageNet dataset across a range of models and report consistent improvements over widely used and strong baselines. We hope our work will help bridge the gap between generative modeling and representation learning.

Related papers

• LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling [23.886038479359918]
  We propose a dataset-free, and unified approach through recurrent posterior sampling utilizing a pretrained latent diffusion model.<n>Our method incorporates the multimodal understanding model to provide sematic priors for the generative model under a task-blind condition.
  arXiv  Detail & Related papers  (2025-07-01T14:25:09Z)
• Continuous Visual Autoregressive Generation via Score Maximization [69.67438563485887]
  We introduce a Continuous VAR framework that enables direct visual autoregressive generation without vector quantization.<n>Within this framework, all we need is to select a strictly proper score and set it as the training objective to optimize.
  arXiv  Detail & Related papers  (2025-05-12T17:58:14Z)
• Generative Data Mining with Longtail-Guided Diffusion [39.460272573196896]
  We develop a proactive longtail discovery process by imagining additional data during training.<n>We leverage these signals as guidance to generate additional training data from a latent diffusion model.<n>Data generated by LTG exhibit semantically meaningful variation, yield significant generalization improvements on image classification benchmarks.
  arXiv  Detail & Related papers  (2025-02-04T03:51:00Z)
• 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)
• Diffusing States and Matching Scores: A New Framework for Imitation Learning [16.941612670582522]
  Adversarial Imitation Learning is traditionally framed as a two-player zero-sum game between a learner and an adversarially chosen cost function.<n> diffusion models have emerged as a non-adversarial alternative to GANs that merely require training a score function via regression.<n>We show our approach outperforms both GAN-style imitation learning baselines and discriminator-free imitation learning baselines across various continuous control problems.
  arXiv  Detail & Related papers  (2024-10-17T17:59:25Z)
• Model Will Tell: Training Membership Inference for Diffusion Models [15.16244745642374]
  Training Membership Inference (TMI) task aims to determine whether a specific sample has been used in the training process of a target model. In this paper, we explore a novel perspective for the TMI task by leveraging the intrinsic generative priors within the diffusion model.
  arXiv  Detail & Related papers  (2024-03-13T12:52:37Z)
• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
  Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI) In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion) Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
  arXiv  Detail & Related papers  (2024-02-15T18:59:18Z)
• ExposureDiffusion: Learning to Expose for Low-light Image Enhancement [87.08496758469835]
  This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks.
  arXiv  Detail & Related papers  (2023-07-15T04:48:35Z)
• Image retrieval outperforms diffusion models on data augmentation [36.559967424331695]
  diffusion models are proposed to augment training datasets for downstream tasks, such as classification. It remains unclear if they generalize enough to improve over directly using the additional data of their pre-training process for augmentation. Personalizing diffusion models towards the target data outperforms simpler prompting strategies. However, using the pre-training data of the diffusion model alone, via a simple nearest-neighbor retrieval procedure, leads to even stronger downstream performance.
  arXiv  Detail & Related papers  (2023-04-20T12:21:30Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• The Deep Generative Decoder: MAP estimation of representations improves modeling of single-cell RNA data [0.0]
  We present a simple generative model that computes model parameters and representations directly via maximum a posteriori (MAP) estimation. The advantages of this approach are its simplicity and its capability to provide representations of much smaller dimensionality than a comparable VAE.
  arXiv  Detail & Related papers  (2021-10-13T12:17:46Z)
• Self-Damaging Contrastive Learning [92.34124578823977]
  Unlabeled data in reality is commonly imbalanced and shows a long-tail distribution. This paper proposes a principled framework called Self-Damaging Contrastive Learning to automatically balance the representation learning without knowing the classes. Our experiments show that SDCLR significantly improves not only overall accuracies but also balancedness.
  arXiv  Detail & Related papers  (2021-06-06T00:04:49Z)
• Negative Data Augmentation [127.28042046152954]
  We show that negative data augmentation samples provide information on the support of the data distribution. We introduce a new GAN training objective where we use NDA as an additional source of synthetic data for the discriminator. Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.
  arXiv  Detail & Related papers  (2021-02-09T20:28:35Z)

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.