Multi-bin Trainable Linear Unit for Fast Image Restoration Networks
arXiv:1807.11389
Abstract
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.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- Binarized Neural Networks
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Learning Activation Functions to Improve Deep Neural Networks
- Lossy Image Compression with Compressive Autoencoders
- MemNet: A Persistent Memory Network for Image Restoration
- Learning Deep CNN Denoiser Prior for Image Restoration
- Multi-Bias Non-linear Activation in Deep Neural Networks
- Single Image Super-Resolution Using Lightweight CNN with Maxout Units