Amazing technological breakthrough possible @S-Logix

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • +91- 81240 01111

Social List

Pre-Trained Image Processing Transformer - 2021

Research Area:  Machine Learning


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 contrastive 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.

Author(s) Name:  Hanting Chen; Yunhe Wang; Tianyu Guo; Chang Xu; Yiping Deng; Zhenhua Liu; Siwei Ma; Chunjing Xu; Chao Xu; Wen Gao

Journal name:  

Conferrence name:  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Publisher name:  IEEE

DOI:  10.1109/CVPR46437.2021.01212

Volume Information: