Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution

Abstract

Constrained image splicing detection and localization (CISDL) is a newly proposed challenging task for image forensics, which investigates two input suspected images and identifies whether one image has suspected regions pasted from the other. In this paper, we propose a novel adversarial learning framework to train the deep matching network for CISDL. Our framework mainly consists of three building blocks: 1) the deep matching network based on atrous convolution (DMAC) aims to generate two high-quality candidate masks which indicate the suspected regions of the two input images, 2) the detection network is designed to rectify inconsistencies between the two corresponding candidate masks, 3) the discriminative network drives the DMAC network to produce masks that are hard to distinguish from ground-truth ones. In DMAC, atrous convolution is adopted to extract features with rich spatial information, the correlation layer based on the skip architecture is proposed to capture hierarchical features, and atrous spatial pyramid pooling is constructed to localize tampered regions at multiple scales. The detection network and the discriminative network act as the losses with auxiliary parameters to supervise the training of DMAC in an adversarial way. Extensive experiments, conducted on 21 generated testing sets and two public datasets, demonstrate the effectiveness of the proposed framework and the superior performance of DMAC.

arXiv comment13 pages, 8 figures

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Rethinking Atrous Convolution for Semantic Image Segmentation
• ADADELTA: An Adaptive Learning Rate Method
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Spectral Normalization for Generative Adversarial Networks
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Adversarial Feature Learning
• Semantic Segmentation using Adversarial Networks
• Adversarial Learning for Semi-Supervised Semantic Segmentation
• Deep Image Homography Estimation
• WarpNet: Weakly Supervised Matching for Single-view Reconstruction
• Deep Matching and Validation Network -- An End-to-End Solution to Constrained Image Splicing Localization and Detection