FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification

• URL: http://arxiv.org/abs/2410.10356v2
• Date: Thu, 31 Oct 2024 12:49:09 GMT
• Title: FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
• Authors: Jingfeng Yao, Wang Cheng, Wenyu Liu, Xinggang Wang,
• Abstract summary: Diffusion Transformers (DiT) suffer from a slow convergence rate. We aim to accelerate DiT training without any architectural modification. We propose FasterDiT, an exceedingly simple and practicable design strategy.
• Score: 35.105593013654
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the following issues in the training process: firstly, certain training strategies do not consistently perform well across different data. Secondly, the effectiveness of supervision at specific timesteps is limited. In response, we propose the following contributions: (1) We introduce a new perspective for interpreting the failure of the strategies. Specifically, we slightly extend the definition of Signal-to-Noise Ratio (SNR) and suggest observing the Probability Density Function (PDF) of SNR to understand the essence of the data robustness of the strategy. (2) We conduct numerous experiments and report over one hundred experimental results to empirically summarize a unified accelerating strategy from the perspective of PDF. (3) We develop a new supervision method that further accelerates the training process of DiT. Based on them, we propose FasterDiT, an exceedingly simple and practicable design strategy. With few lines of code modifications, it achieves 2.30 FID on ImageNet 256 resolution at 1000k iterations, which is comparable to DiT (2.27 FID) but 7 times faster in training.

Related papers

• Accelerating Augmentation Invariance Pretraining [7.772780341646099]
  We tackle the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs) We propose an acceleration framework, leveraging ViT's unique ability to generalize across inputs of varying sequence lengths. Our method employs a mix of sequence compression strategies, including randomized token dropout and flexible patch scaling, to reduce the cost of gradient estimation and accelerate convergence.
  arXiv  Detail & Related papers  (2024-10-27T21:53:33Z)
• Efficient Stagewise Pretraining via Progressive Subnetworks [53.00045381931778]
  The prevailing view suggests that stagewise dropping strategies, such as layer dropping, are ineffective when compared to stacking-based approaches. This paper challenges this notion by demonstrating that, with proper design, dropping strategies can be competitive, if not better, than stacking methods. We propose an instantiation of this framework - Random Part Training (RAPTR) - that selects and trains only a random subnetwork at each step, progressively increasing the size in stages.
  arXiv  Detail & Related papers  (2024-02-08T18:49:09Z)
• Efficient Diffusion Training via Min-SNR Weighting Strategy [78.5801305960993]
  We treat the diffusion training as a multi-task learning problem and introduce a simple yet effective approach referred to as Min-SNR-$gamma$. Our results demonstrate a significant improvement in converging speed, 3.4$times$ faster than previous weighting strategies. It is also more effective, achieving a new record FID score of 2.06 on the ImageNet $256times256$ benchmark using smaller architectures than that employed in previous state-of-the-art.
  arXiv  Detail & Related papers  (2023-03-16T17:59:56Z)
• Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training [110.79400526706081]
  Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage limit their generalization. Previous compression algorithms usually start from the pre-trained dense models and only focus on efficient inference. This paper proposes an end-to-end efficient training framework from three sparse perspectives, dubbed Tri-Level E-ViT.
  arXiv  Detail & Related papers  (2022-11-19T21:15:47Z)
• Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
  Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples. We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment. We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
  arXiv  Detail & Related papers  (2022-03-23T06:24:31Z)
• Faster Meta Update Strategy for Noise-Robust Deep Learning [62.08964100618873]
  We introduce a novel Faster Meta Update Strategy (FaMUS) to replace the most expensive step in the meta gradient with a faster layer-wise approximation. We show our method is able to save two-thirds of the training time while still maintaining the comparable or achieving even better generalization performance.
  arXiv  Detail & Related papers  (2021-04-30T16:19:07Z)

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.