Reconstruction-free Image Compression for Machine Vision via Knowledge Transfer

Abstract

Reconstruction-free image compression for machine vision aims to perform machine vision tasks directly on compressed-domain representations instead of reconstructed images. Existing reports have validated the feasibility of compressed-domain machine vision. However, we observe that when using recent learned compression models, the performance gap between compressed-domain and pixel-domain vision tasks is still large due to the lack of some natural inductive biases in pixel-domain convolutional neural networks. In this paper, we attempt to address this problem by transferring knowledge from pixel domain to compressed domain. A knowledge transfer loss defined at both output level and feature level is proposed to narrow the gap between compressed domain and pixel domain. In addition, we modify neural networks for pixel-domain vision tasks to better suit compressed-domain inputs. Experimental results on several machine vision tasks show that the proposed method improves the accuracy of compressed-domain vision tasks significantly, which even outperforms learning on reconstructed images while avoiding the computational cost of image reconstruction.