Wavelet Feature Maps Compression for Image-to-Image CNNs.

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

Research output: Working paper/PreprintPreprint


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 on various tasks, that benefit from high-resolution input, and 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.
Original languageEnglish
StatePublished - 16 Oct 2022


Dive into the research topics of 'Wavelet Feature Maps Compression for Image-to-Image CNNs.'. Together they form a unique fingerprint.

Cite this