No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves

• URL: http://arxiv.org/abs/2505.02831v4
• Date: Sat, 17 May 2025 13:07:16 GMT
• Title: No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
• Authors: Dengyang Jiang, Mengmeng Wang, Liuzhuozheng Li, Lei Zhang, Haoyu Wang, Wei Wei, Guang Dai, Yanning Zhang, Jingdong Wang,
• Abstract summary: Self-Representation Alignment (SRA) is a simple yet straightforward method that obtains representation guidance through a self-distillation manner.<n> Experimental results indicate that applying SRA to DiTs and SiTs yields consistent performance improvements.
• Score: 59.79343544931784
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies have demonstrated that learning a meaningful internal representation can both accelerate generative training and enhance the generation quality of diffusion transformers. However, existing approaches necessitate to either introduce an external and complex representation training framework or rely on a large-scale, pre-trained representation foundation model to provide representation guidance during the original generative training process. In this study, we posit that the unique discriminative process inherent to diffusion transformers enables them to offer such guidance without requiring external representation components. We therefore propose Self-Representation Alignment (SRA), a simple yet straightforward method that obtains representation guidance through a self-distillation manner. Specifically, SRA aligns the output latent representation of the diffusion transformer in the earlier layer with higher noise to that in the later layer with lower noise to progressively enhance the overall representation learning during only the generative training process. Experimental results indicate that applying SRA to DiTs and SiTs yields consistent performance improvements. Moreover, SRA not only significantly outperforms approaches relying on auxiliary, complex representation training frameworks but also achieves performance comparable to methods that are heavily dependent on powerful external representation priors.

Related papers

• DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning [53.27049077100897]
  generative pre-training has been shown to yield discriminative representations, paving the way towards unified visual generation and understanding.<n>This work introduces self-conditioning, a mechanism that internally leverages the rich semantics inherent in denoising network to guide its own decoding layers.<n>Results are compelling: our method boosts both generation FID and recognition accuracy with 1% computational overhead and generalizes across diverse diffusion architectures.
  arXiv  Detail & Related papers  (2025-05-16T08:47:16Z)
• GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution [15.563111624900865]
  GuideSR is a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity.<n>Our approach consistently outperforms existing methods across various reference-based metrics including PSNR, SSIM, LPIPS, DISTS and FID.
  arXiv  Detail & Related papers  (2025-05-01T17:48:25Z)
• Efficient Generative Model Training via Embedded Representation Warmup [6.783363935446626]
  Diffusion models excel at generating high-dimensional data but fall short in training efficiency and representation quality compared to self-supervised methods.<n>We identify a key bottleneck: the underutilization of high-quality, semantically rich representations during training.<n>We propose Embedded Representation Warmup (ERW), a plug-and-play framework where in the first stage we get the ERW module.
  arXiv  Detail & Related papers  (2025-04-14T12:43:17Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators [12.053125079460234]
  We show how modern T2I generators can be used to simulate arbitrary interventions over such environmental factors. Our empirical findings demonstrate that modern T2I generators like Stable Diffusion can indeed be used as a powerful interventional data augmentation mechanism.
  arXiv  Detail & Related papers  (2022-12-21T18:07:39Z)
• XAI for Transformers: Better Explanations through Conservative Propagation [60.67748036747221]
  We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. Our proposal can be seen as a proper extension of the well-established LRP method to Transformers.
  arXiv  Detail & Related papers  (2022-02-15T10:47:11Z)
• High-Fidelity Synthesis with Disentangled Representation [60.19657080953252]
  We propose an Information-Distillation Generative Adrial Network (ID-GAN) for disentanglement learning and high-fidelity synthesis. Our method learns disentangled representation using VAE-based models, and distills the learned representation with an additional nuisance variable to the separate GAN-based generator for high-fidelity synthesis. Despite the simplicity, we show that the proposed method is highly effective, achieving comparable image generation quality to the state-of-the-art methods using the disentangled representation.
  arXiv  Detail & Related papers  (2020-01-13T14:39:40Z)

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.