Efficient Training with Denoised Neural Weights

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Yifan, Zhan, Zheng, Li, Yanyu, Idelbayev, Yerlan, Zharkov, Andrey, Aberman, Kfir, Tulyakov, Sergey, Wang, Yanzhi, Ren, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910529773109248
author Gong, Yifan
Zhan, Zheng
Li, Yanyu
Idelbayev, Yerlan
Zharkov, Andrey
Aberman, Kfir
Tulyakov, Sergey
Wang, Yanzhi
Ren, Jian
author_facet Gong, Yifan
Zhan, Zheng
Li, Yanyu
Idelbayev, Yerlan
Zharkov, Andrey
Aberman, Kfir
Tulyakov, Sergey
Wang, Yanzhi
Ren, Jian
contents Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming and prone to human error. To overcome such limitations, this work takes a novel step towards building a weight generator to synthesize the neural weights for initialization. We use the image-to-image translation task with generative adversarial networks (GANs) as an example due to the ease of collecting model weights spanning a wide range. Specifically, we first collect a dataset with various image editing concepts and their corresponding trained weights, which are later used for the training of the weight generator. To address the different characteristics among layers and the substantial number of weights to be predicted, we divide the weights into equal-sized blocks and assign each block an index. Subsequently, a diffusion model is trained with such a dataset using both text conditions of the concept and the block indexes. By initializing the image translation model with the denoised weights predicted by our diffusion model, the training requires only 43.3 seconds. Compared to training from scratch (i.e., Pix2pix), we achieve a 15x training time acceleration for a new concept while obtaining even better image generation quality.
format Preprint
id arxiv_https___arxiv_org_abs_2407_11966
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Training with Denoised Neural Weights
Gong, Yifan
Zhan, Zheng
Li, Yanyu
Idelbayev, Yerlan
Zharkov, Andrey
Aberman, Kfir
Tulyakov, Sergey
Wang, Yanzhi
Ren, Jian
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming and prone to human error. To overcome such limitations, this work takes a novel step towards building a weight generator to synthesize the neural weights for initialization. We use the image-to-image translation task with generative adversarial networks (GANs) as an example due to the ease of collecting model weights spanning a wide range. Specifically, we first collect a dataset with various image editing concepts and their corresponding trained weights, which are later used for the training of the weight generator. To address the different characteristics among layers and the substantial number of weights to be predicted, we divide the weights into equal-sized blocks and assign each block an index. Subsequently, a diffusion model is trained with such a dataset using both text conditions of the concept and the block indexes. By initializing the image translation model with the denoised weights predicted by our diffusion model, the training requires only 43.3 seconds. Compared to training from scratch (i.e., Pix2pix), we achieve a 15x training time acceleration for a new concept while obtaining even better image generation quality.
title Efficient Training with Denoised Neural Weights
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2407.11966