Multi-bin Trainable Linear Unit for Fast Image Restoration Networks
This work addresses the need for faster and more memory-efficient image restoration networks, which is crucial for real-time applications, though it appears incremental as it builds on existing network architectures with a new activation function.
The authors tackled the problem of making image restoration networks more efficient by proposing a novel activation function, the multi-bin trainable linear unit (MTLU), which increases nonlinear modeling capacity while using lighter and shallower networks. They validated this on image denoising (FDnet) and super-resolution (FSRnet) benchmarks, achieving large improvements in memory and runtime over state-of-the-art methods with comparable or better PSNR accuracies.
Tremendous advances in image restoration tasks such as denoising and super-resolution have been achieved using neural networks. Such approaches generally employ very deep architectures, large number of parameters, large receptive fields and high nonlinear modeling capacity. In order to obtain efficient and fast image restoration networks one should improve upon the above mentioned requirements. In this paper we propose a novel activation function, the multi-bin trainable linear unit (MTLU), for increasing the nonlinear modeling capacity together with lighter and shallower networks. We validate the proposed fast image restoration networks for image denoising (FDnet) and super-resolution (FSRnet) on standard benchmarks. We achieve large improvements in both memory and runtime over current state-of-the-art for comparable or better PSNR accuracies.