DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework
This addresses storage and power efficiency issues for DNN-based smart IoT systems, though it is incremental as it adapts an existing compression approach for a specific domain.
The paper tackles the problem that JPEG compression is suboptimal for deep neural networks (DNNs) in IoT systems by developing DeepN-JPEG, a tailored compression framework that achieves ~3.5x higher compression rates than JPEG while maintaining the same image recognition accuracy.
As one of most fascinating machine learning techniques, deep neural network (DNN) has demonstrated excellent performance in various intelligent tasks such as image classification. DNN achieves such performance, to a large extent, by performing expensive training over huge volumes of training data. To reduce the data storage and transfer overhead in smart resource-limited Internet-of-Thing (IoT) systems, effective data compression is a "must-have" feature before transferring real-time produced dataset for training or classification. While there have been many well-known image compression approaches (such as JPEG), we for the first time find that a human-visual based image compression approach such as JPEG compression is not an optimized solution for DNN systems, especially with high compression ratios. To this end, we develop an image compression framework tailored for DNN applications, named "DeepN-JPEG", to embrace the nature of deep cascaded information process mechanism of DNN architecture. Extensive experiments, based on "ImageNet" dataset with various state-of-the-art DNNs, show that "DeepN-JPEG" can achieve ~3.5x higher compression rate over the popular JPEG solution while maintaining the same accuracy level for image recognition, demonstrating its great potential of storage and power efficiency in DNN-based smart IoT system design.