Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques

Abstract

This is the report for the PRIM project in Telecom Paris. This report is about applications based on spatial-frequency transform and deep learning techniques. In this report, there are two main works. The first work is about the enhanced JPEG compression method based on deep learning. we propose a novel method to highly enhance the JPEG compression by transmitting fewer image data at the sender's end. At the receiver's end, we propose a DC recovery algorithm together with the deep residual learning framework to recover images with high quality. The second work is about adversarial examples defenses based on signal processing. We propose the wavelet extension method to extend image data features, which makes it more difficult to generate adversarial examples. We further adopt wavelet denoising to reduce the influence of the adversarial perturbations. With intensive experiments, we demonstrate that both works are effective in their application scenarios.

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• End-to-end Optimized Image Compression
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• The Space of Transferable Adversarial Examples
• Adversarial Examples for Evaluating Reading Comprehension Systems
• On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
• Defending against Adversarial Images using Basis Functions Transformations
• Recovering Missing Coefficients in DCT-Transformed Images