Pre-Trained Image Processing Transformer
Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu
Abstract
As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly contributed to the representation ability of transformer and its variant architectures. In this paper, we study the low-level computer vision task (e.g., denoising, super-resolution and deraining) and develop a new pre-trained model, namely, image processing transformer (IPT). To maximally excavate the capability of transformer, we present to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs. The IPT model is trained on these images with multi-heads and multi-tails. In addition, the constructive learning is introduced for well adapting to different image processing tasks. The pre-trained model can therefore efficiently employed on desired task after fine-tuning. With only one pre-trained model, IPT outperforms the current state-of-the-art methods on various low-level benchmarks. Code is available at https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/IPT
BibTeX
@inproceedings{cvpr2021_pretrainedimagep,
title = {Pre-Trained Image Processing Transformer},
author = {Hanting Chen and Yunhe Wang and Tianyu Guo and Chang Xu and Yiping Deng and Zhenhua Liu and Siwei Ma and Chunjing Xu and Chao Xu and Wen Gao},
booktitle = {CVPR 2021},
year = {2021}
}