Picking Up Quantization Steps for Compressed Image Classification
This addresses a practical issue for real-world applications where image compression is common, but it is incremental as it builds on existing methods by incorporating coding parameters.
The paper tackles the problem of deep neural networks being sensitive to compressed images, which can cause classification failures after saving images as compressed files, by using quantization steps from compressed files to improve classification performance, achieving significant improvements on CIFAR-10, CIFAR-100, and ImageNet.
The sensitivity of deep neural networks to compressed images hinders their usage in many real applications, which means classification networks may fail just after taking a screenshot and saving it as a compressed file. In this paper, we argue that neglected disposable coding parameters stored in compressed files could be picked up to reduce the sensitivity of deep neural networks to compressed images. Specifically, we resort to using one of the representative parameters, quantization steps, to facilitate image classification. Firstly, based on quantization steps, we propose a novel quantization aware confidence (QAC), which is utilized as sample weights to reduce the influence of quantization on network training. Secondly, we utilize quantization steps to alleviate the variance of feature distributions, where a quantization aware batch normalization (QABN) is proposed to replace batch normalization of classification networks. Extensive experiments show that the proposed method significantly improves the performance of classification networks on CIFAR-10, CIFAR-100, and ImageNet. The code is released on https://github.com/LiMaPKU/QSAM.git