当前位置: X-MOL 学术IEEE J. Sel. Top. Signal Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automated Design of Neural Network Architectures with Reinforcement Learning for Detection of Global Manipulations
IEEE Journal of Selected Topics in Signal Processing ( IF 8.7 ) Pub Date : 2020-08-01 , DOI: 10.1109/jstsp.2020.2998401
Yifang Chen , Zheng Wang , Z. Jane Wang , Xiangui Kang

Deep Convolutional Neural Networks (DCNNs) have been widely used in detection of global manipulations. However, designing effective DCNNs for specific image forensics tasks generally requires domain knowledge and experience gained from abundant experiments, which is time-consuming and labor-expensive. Approaches of automated network designing have been proposed for image classification tasks which are image-content focused, however they may not be suitable to image forensics tasks which rely on identifying subtle traces left by certain image operations. In this paper, we make the first attempt to automate the neural network architecture design for detection of global manipulations. The process of constructing a network is modeled as sequentially selecting optimal architecture modules to generate high-performing CNNs for specific forensic tasks through reinforcement learning. The module-based search space is proposed to make the designing process efficient. Advanced connection patterns (e.g., dense connectivity), which were shown preferred for global manipulation detections, are included in the modules to improve the representational power of the network. Experimental results show that the proposed approach can adaptively construct effective CNN architectures for two common forensic tasks, including multi-purpose forensics and the processing history detection. The auto-designed networks can outperform the state-of-the-art manually designed networks.

中文翻译:

使用强化学习自动设计神经网络架构以检测全局操作

深度卷积神经网络 (DCNN) 已广泛用于检测全局操作。然而,为特定的图像取证任务设计有效的 DCNN 通常需要从大量实验中获得的领域知识和经验,这既费时又费力。已经针对图像内容集中的图像分类任务提出了自动化网络设计方法,但是它们可能不适合依赖于识别某些图像操作留下的细微痕迹的图像取证任务。在本文中,我们首次尝试自动化用于检测全局操作的神经网络架构设计。构建网络的过程被建模为依次选择最佳架构模块,以通过强化学习为特定的取证任务生成高性能的 CNN。提出了基于模块的搜索空间,以提高设计过程的效率。高级连接模式(例如,密集连接)显示为全局操作检测的首选,包含在模块中以提高网络的表示能力。实验结果表明,所提出的方法可以为两种常见的取证任务自适应地构建有效的 CNN 架构,包括多用途取证和处理历史检测。自动设计的网络可以胜过最先进的手动设计的网络。提出了基于模块的搜索空间,以提高设计过程的效率。高级连接模式(例如,密集连接)显示为全局操作检测的首选,包含在模块中以提高网络的表示能力。实验结果表明,所提出的方法可以为两种常见的取证任务自适应地构建有效的 CNN 架构,包括多用途取证和处理历史检测。自动设计的网络可以胜过最先进的手动设计的网络。提出了基于模块的搜索空间,以提高设计过程的效率。高级连接模式(例如,密集连接)显示为全局操作检测的首选,包含在模块中以提高网络的表示能力。实验结果表明,所提出的方法可以为两种常见的取证任务自适应地构建有效的 CNN 架构,包括多用途取证和处理历史检测。自动设计的网络可以胜过最先进的手动设计的网络。实验结果表明,所提出的方法可以为两种常见的取证任务自适应地构建有效的 CNN 架构,包括多用途取证和处理历史检测。自动设计的网络可以胜过最先进的手动设计的网络。实验结果表明,所提出的方法可以为两种常见的取证任务自适应地构建有效的 CNN 架构,包括多用途取证和处理历史检测。自动设计的网络可以胜过最先进的手动设计的网络。
更新日期:2020-08-01
down
wechat
bug