Data Upcycling Knowledge Distillation for Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yun, Li, Wei, Li, Simiao, Chen, Hanting, Tu, Zhijun, Wang, Wenjia, Jing, Bingyi, Lin, Shaohui, Hu, Jie
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929329135419392
author Zhang, Yun
Li, Wei
Li, Simiao
Chen, Hanting
Tu, Zhijun
Wang, Wenjia
Jing, Bingyi
Lin, Shaohui
Hu, Jie
author_facet Zhang, Yun
Li, Wei
Li, Simiao
Chen, Hanting
Tu, Zhijun
Wang, Wenjia
Jing, Bingyi
Lin, Shaohui
Hu, Jie
contents Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models. However, current KD methods for super-resolution (SR) networks overlook the nature of SR task that the outputs of the teacher model are noisy approximations to the ground-truth distribution of high-quality images (GT), which shades the teacher model's knowledge to result in limited KD effects. To utilize the teacher model beyond the GT upper-bound, we present the Data Upcycling Knowledge Distillation (DUKD), to transfer the teacher model's knowledge to the student model through the upcycled in-domain data derived from training data. Besides, we impose label consistency regularization to KD for SR by the paired invertible augmentations to improve the student model's performance and robustness. Comprehensive experiments demonstrate that the DUKD method significantly outperforms previous arts on several SR tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2309_14162
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Data Upcycling Knowledge Distillation for Image Super-Resolution
Zhang, Yun
Li, Wei
Li, Simiao
Chen, Hanting
Tu, Zhijun
Wang, Wenjia
Jing, Bingyi
Lin, Shaohui
Hu, Jie
Computer Vision and Pattern Recognition
Artificial Intelligence
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models. However, current KD methods for super-resolution (SR) networks overlook the nature of SR task that the outputs of the teacher model are noisy approximations to the ground-truth distribution of high-quality images (GT), which shades the teacher model's knowledge to result in limited KD effects. To utilize the teacher model beyond the GT upper-bound, we present the Data Upcycling Knowledge Distillation (DUKD), to transfer the teacher model's knowledge to the student model through the upcycled in-domain data derived from training data. Besides, we impose label consistency regularization to KD for SR by the paired invertible augmentations to improve the student model's performance and robustness. Comprehensive experiments demonstrate that the DUKD method significantly outperforms previous arts on several SR tasks.
title Data Upcycling Knowledge Distillation for Image Super-Resolution
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2309.14162