Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

by   Tianshui Chen, et al.

Accelerating deep neural networks (DNNs) has been attracting increasing attention as it can benefit a wide range of applications, e.g., enabling mobile systems with limited computing resources to own powerful visual recognition ability. A practical strategy to this goal usually relies on a two-stage process: operating on the trained DNNs (e.g., approximating the convolutional filters with tensor decomposition) and fine-tuning the amended network, leading to difficulty in balancing the trade-off between acceleration and maintaining recognition performance. In this work, aiming at a general and comprehensive way for neural network acceleration, we develop a Wavelet-like Auto-Encoder (WAE) that decomposes the original input image into two low-resolution channels (sub-images) and incorporate the WAE into the classification neural networks for joint training. The two decomposed channels, in particular, are encoded to carry the low-frequency information (e.g., image profiles) and high-frequency (e.g., image details or noises), respectively, and enable reconstructing the original input image through the decoding process. Then, we feed the low-frequency channel into a standard classification network such as VGG or ResNet and employ a very lightweight network to fuse with the high-frequency channel to obtain the classification result. Compared to existing DNN acceleration solutions, our framework has the following advantages: i) it is tolerant to any existing convolutional neural networks for classification without amending their structures; ii) the WAE provides an interpretable way to preserve the main components of the input image for classification.


page 3

page 6


Wavelet-Attention CNN for Image Classification

The feature learning methods based on convolutional neural network (CNN)...

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

We present a novel direction-aware feature-level frequency decomposition...

High Frequency Residual Learning for Multi-Scale Image Classification

We present a novel high frequency residual learning framework, which lea...

FUNN: Flexible Unsupervised Neural Network

Deep neural networks have demonstrated high accuracy in image classifica...

Animating Through Warping: an Efficient Method for High-Quality Facial Expression Animation

Advances in deep neural networks have considerably improved the art of a...

WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields

Neural Radiance Field (NeRF) has shown impressive performance in novel v...

A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks

Deep learning and especially the use of Deep Neural Networks (DNNs) prov...

Please sign up or login with your details

Forgot password? Click here to reset