TY - GEN
T1 - Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation
AU - Li, Juncheng
AU - Yang, Hanhui
AU - Yi, Qiaosi
AU - Fang, Faming
AU - Gao, Guangwei
AU - Zeng, Tieyong
AU - Zhang, Guixu
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Single image denoising (SID) has achieved significant breakthroughs with the development of deep learning. However, the proposed methods are often accompanied by plenty of parameters, which greatly limits their application scenarios. Different from previous works that blindly increase the depth of the network, we explore the degradation mechanism of the noisy image and propose a lightweight Multiple Degradation and Reconstruction Network (MDRN) to progressively remove noise. Meanwhile, we propose two novel Heterogeneous Knowledge Distillation Strategies (HMDS) to enable MDRN to learn richer and more accurate features from heterogeneous models, which make it possible to reconstruct higher-quality denoised images under extreme conditions. Extensive experiments show that our MDRN achieves favorable performance against other SID models with fewer parameters. Meanwhile, plenty of ablation studies demonstrate that the introduced HMDS can improve the performance of tiny models or the model under high noise levels, which is extremely useful for related applications.
AB - Single image denoising (SID) has achieved significant breakthroughs with the development of deep learning. However, the proposed methods are often accompanied by plenty of parameters, which greatly limits their application scenarios. Different from previous works that blindly increase the depth of the network, we explore the degradation mechanism of the noisy image and propose a lightweight Multiple Degradation and Reconstruction Network (MDRN) to progressively remove noise. Meanwhile, we propose two novel Heterogeneous Knowledge Distillation Strategies (HMDS) to enable MDRN to learn richer and more accurate features from heterogeneous models, which make it possible to reconstruct higher-quality denoised images under extreme conditions. Extensive experiments show that our MDRN achieves favorable performance against other SID models with fewer parameters. Meanwhile, plenty of ablation studies demonstrate that the introduced HMDS can improve the performance of tiny models or the model under high noise levels, which is extremely useful for related applications.
UR - https://www.scopus.com/pages/publications/85136030308
U2 - 10.1109/CVPRW56347.2022.00071
DO - 10.1109/CVPRW56347.2022.00071
M3 - 会议稿件
AN - SCOPUS:85136030308
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 557
EP - 566
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
PB - IEEE Computer Society
T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Y2 - 19 June 2022 through 24 June 2022
ER -