DiffiT: Diffusion Vision Transformers for Image Generation

• URL: http://arxiv.org/abs/2312.02139v3
• Date: Thu, 29 Aug 2024 03:09:40 GMT
• Title: DiffiT: Diffusion Vision Transformers for Image Generation
• Authors: Ali Hatamizadeh, Jiaming Song, Guilin Liu, Jan Kautz, Arash Vahdat,
• Abstract summary: Vision Transformer (ViT) has demonstrated strong modeling capabilities and scalability, especially for recognition tasks. We study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT) DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency.
• Score: 88.08529836125399
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities and scalability, especially for recognition tasks. In this paper, we study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT). Specifically, we propose a methodology for finegrained control of the denoising process and introduce the Time-dependant Multihead Self Attention (TMSA) mechanism. DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency. We also propose latent and image space DiffiT models and show SOTA performance on a variety of class-conditional and unconditional synthesis tasks at different resolutions. The Latent DiffiT model achieves a new SOTA FID score of 1.73 on ImageNet256 dataset while having 19.85%, 16.88% less parameters than other Transformer-based diffusion models such as MDT and DiT,respectively. Code: https://github.com/NVlabs/DiffiT

Related papers

• 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)
• Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models [26.926712014346432]
  This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Our method's efficacy is demonstrated on the class-conditional ImageNet generation benchmark, setting new state-of-the-art FID scores of 1.70 on ImageNet 256 x 256 and 2.89 on ImageNet 512 x 512.
  arXiv  Detail & Related papers  (2024-06-13T17:59:58Z)
• TerDiT: Ternary Diffusion Models with Transformers [83.94829676057692]
  TerDiT is a quantization-aware training scheme for ternary diffusion models with transformers. We focus on the ternarization of DiT networks and scale model sizes from 600M to 4.2B.
  arXiv  Detail & Related papers  (2024-05-23T17:57:24Z)
• TFormer: A Transmission-Friendly ViT Model for IoT Devices [23.67389080796814]
  This paper proposes a transmission-friendly ViT model, TFormer, for deployment on resource-constrained IoT devices with the assistance of a cloud server. Experimental results on the ImageNet-1K, MS COCO, and ADE20K datasets for image classification, object detection, and semantic segmentation tasks demonstrate that the proposed model outperforms other state-of-the-art models.
  arXiv  Detail & Related papers  (2023-02-15T15:36:10Z)
• Improving Vision Transformers by Revisiting High-frequency Components [106.7140968644414]
  We show that Vision Transformer (ViT) models are less effective in capturing the high-frequency components of images than CNN models. To compensate, we propose HAT, which directly augments high-frequency components of images via adversarial training. We show that HAT can consistently boost the performance of various ViT models.
  arXiv  Detail & Related papers  (2022-04-03T05:16:51Z)
• Efficient Vision Transformers via Fine-Grained Manifold Distillation [96.50513363752836]
  Vision transformer architectures have shown extraordinary performance on many computer vision tasks. Although the network performance is boosted, transformers are often required more computational resources. We propose to excavate useful information from the teacher transformer through the relationship between images and the divided patches.
  arXiv  Detail & Related papers  (2021-07-03T08:28:34Z)
• Vision Transformers are Robust Learners [65.91359312429147]
  We study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. We present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners.
  arXiv  Detail & Related papers  (2021-05-17T02:39:22Z)

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.