Skip to yearly menu bar Skip to main content


Wavelet Feature Maps Compression for Image-to-Image CNNs

Shahaf E. Finder · Yair Zohav · Maor Ashkenazi · Eran Treister

Hall J (level 1) #638

Keywords: [ convolutional neural networks ] [ Wavelet Transform ] [ Quantization ]


Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs well for classification, it may cause severe performance degradation in image-to-image tasks such as semantic segmentation and depth estimation. In this paper, we propose Wavelet Compressed Convolution (WCC)---a novel approach for high-resolution activation maps compression integrated with point-wise convolutions, which are the main computational cost of modern architectures. To this end, we use an efficient and hardware-friendly Haar-wavelet transform, known for its effectiveness in image compression, and define the convolution on the compressed activation map. We experiment with various tasks that benefit from high-resolution input. By combining WCC with light quantization, we achieve compression rates equivalent to 1-4bit activation quantization with relatively small and much more graceful degradation in performance. Our code is available at

Chat is not available.