Feature Consistency Training with JPEG Compressed Images

Sheng Wan*, Tung Yu Wu, Heng Wei Hsu, Wing Hung Wong, Chen Yi Lee


    研究成果: Article同行評審


    Deep neural networks (DNNs) are recently found to be vulnerable to JPEG compression artifacts, which distort the feature representations of DNNs leading to serious accuracy degradation. Most existing training methods which aim to address this problem add compressed images to the training data to enhance the robustness of DNNs. However, their improvements are limited since these methods usually regard the compressed images as new training samples instead of distorted samples. The feature distortions between the raw images and the compressed images are not investigated. In this work, we propose a new training method, called Feature Consistency Training, that is designed to minimize the feature distortions caused by JPEG artifacts. At each training iteration, we simultaneously input a raw image and its compressed version with a randomly sampled quality into a DNN model and extract the features from the internal layers. By adding feature consistency constraint to the objective function, the feature distortions in the representation space are minimized in order to learn robust filters. Besides, we present a residual mapping block which takes the quality factor of the compressed image as an additional information to further reduce the feature distortion. Extensive experiments demonstrate that our method outperforms several existed training methods on JPEG compressed images. Furthermore, DNN models trained by our method are found to be more robust to unseen distortions.

    頁(從 - 到)4769-4780
    期刊IEEE Transactions on Circuits and Systems for Video Technology
    出版狀態Published - 十二月 2020


    深入研究「Feature Consistency Training with JPEG Compressed Images」主題。共同形成了獨特的指紋。