Contrastive Learning for Low-light Raw Denoising

no code implementations • 5 May 2023 • Taoyong Cui, Yuhan Dong

Inspired by the success of contrastive learning used in some high-level computer vision tasks, we bring in this idea to the low-level denoising task.

Contrastive Learning Denoising +1

TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks

no code implementations • 25 Nov 2022 • Taoyong Cui, Jianze Li, Yuhan Dong, Li Liu

In the first stage, we propose a novel algorithm called polar decomposition-based orthogonal initialization (PDOI) to find a good initialization for the orthogonal optimization.