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

By Tianshui Chen, Liang Lin, Wangmeng Zuo, Xiaonan Luo, Lei Zhang. 2017

59 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Paraphrasing Complex Network: Network Compression via Factor Transfer (2018, background): “Although many researchers have studied DNNs for their application in various fields, high-performance DNNs generally require a vast amount of computational power and storage, which makes them difficult to be used in embedded systems that have limited resources (Chen et al., 2017).”
Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding (2018, background): “/github.com/HCPLab-SYSU/HSE. 2 RELATED WORK 2.1 Fine-grained image recognition Recent progress on image classi˙cation mainly bene˙ted from the advancement of deep Convolutional Neural Networks (CNNs) [3, 4, 11, 22, 23, 35] that learned powerful feature representation via stacking multiple nonlinear ”
ELASTIC: Improving CNNs With Dynamic Scaling Policies (2018, methodology): “In addition, [4] used 2 CNNs to deal with high and low frequencies, and [40] proposed to adaptively choose from 2 CNNs with different capacity.”