Feature-Domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution

Feature-Domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution

Convolutional neural network-based single image super-resolution (SISR) involves numerous parameters and high computational expenses to ensure improved performance, limiting its applicability in resource-constrained devices such as mobile phones. Knowledge distillation (KD), which transfers useful k...

Full description

Bibliographic Details
Main Authors: Hyeon-Cheol Moon, Jae-Gon Kim, Jinwoo Jeong, Sungjei Kim
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Contrastive learning
efficient super-resolution
feature distillation
knowledge distillation
single image super-resolution
Online Access:https://ieeexplore.ieee.org/document/10327726/

Internet

https://ieeexplore.ieee.org/document/10327726/

Similar Items