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

arXiv: https://arxiv.org/abs/1712.07493 · HTML: https://mlsanity.com/paper/1712.07493/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2017.

## Built on by (most cited first, 8 of 8)

- [Wavelet Score-Based Generative Modeling](https://mlsanity.com/paper/2208.05003/) (2022)
- [Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation](https://mlsanity.com/paper/2203.06321/) (2022)
- [Learning multi-scale local conditional probability models of images](https://mlsanity.com/paper/2303.02984/) (2023)
- [Continual Learning in the Frequency Domain](https://mlsanity.com/paper/2410.06645/) (2024)
- [Divergences in Color Perception between Deep Neural Networks and Humans](https://mlsanity.com/paper/2309.05809/) (2023)
- [Laplacian Pyramid-like Autoencoder](https://mlsanity.com/paper/2208.12484/) (2022)
- [WavPool: A New Block for Deep Neural Networks](https://mlsanity.com/paper/2306.08734/) (2023)
- [CNNs for JPEGs: A Study in Computational Cost](https://mlsanity.com/paper/2309.11417/) (2023)

## Abstract (arXiv)

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.