Deep Selector-JPEG: Adaptive JPEG Image Compression for Computer Vision in Image classification with Human Vision Criteria
This addresses the issue of inefficient image compression for computer vision systems, offering an incremental improvement by adapting JPEG for both human and machine vision needs.
The paper tackles the problem of JPEG compression for computer vision applications by introducing Deep Selector-JPEG, an adaptive method that selects quality factors to optimize compression ratio and classification accuracy while meeting human vision criteria, achieving accuracy gains of 0.2% to 1% at the same compression ratios compared to standard JPEG.
With limited storage/bandwidth resources, input images to Computer Vision (CV) applications that use Deep Neural Networks (DNNs) are often encoded with JPEG that is tailored to Human Vision (HV). This paper presents Deep Selector-JPEG, an adaptive JPEG compression method that targets image classification while satisfying HV criteria. For each image, Deep Selector-JPEG selects adaptively a Quality Factor (QF) to compress the image so that a good trade-off between the Compression Ratio (CR) and DNN classifier Accuracy (Rate-Accuracy performance) can be achieved over a set of images for a variety of DNN classifiers while the MS-SSIM of such compressed image is greater than a threshold value predetermined by HV with a high probability. Deep Selector-JPEG is designed via light-weighted or heavy-weighted selector architectures. Experimental results show that in comparison with JPEG at the same CR, Deep Selector-JPEG achieves better Rate-Accuracy performance over the ImageNet validation set for all tested DNN classifiers with gains in classification accuracy between 0.2% and 1% at the same CRs while satisfying HV constraints. Deep Selector-JPEG can also roughly provide the original classification accuracy at higher CRs.