arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.09152cs.CV
收藏

SSIMLayer:通过非线性结构相似性实现鲁棒的深度表示学习

SSIMLayer: Towards Robust Deep Representation Learning via Nonlinear Structural Similarity

Institute for Intelligent Systems Research and Innovation (IISRI)(智能系统研究与创新研究所(IISRI));Deakin University(迪肯大学)

Ahmed Abobakr, Mohammed Hossny, Saeid Nahavandi

摘要:

更深的卷积神经网络提供更大的能力来近似复杂的映射函数。然而,增加网络深度会给训练带来困难,并增加模型的复杂性。本文提出了一种新的非线性计算层的相当高的容量的深度卷积神经网络架构。该层执行一组综合卷积操作,通过专注于学习其输入中的结构信息来模仿人类视觉系统(HVS)的整体功能。其计算的核心是在允许内核学习匹配结构信息的设置中评估结构相似性度量(SSIM)的组件。所提出的SSIMLayer本质上是非线性的,因此,它不需要后续的非线性变换。在CIFAR-10基准测试上进行的实验表明,SSIMLayer提供了比传统卷积层更好的收敛性,绕过了非线性变换的需要,并对噪声扰动和对抗攻击表现出更强的鲁棒性。

英文摘要:

Deeper convolutional neural networks provide more capacity to approximate complex mapping functions. However, increasing network depth imposes difficulties on training and increases model complexity. This paper presents a new nonlinear computational layer of considerably high capacity to the deep convolutional neural network architectures. This layer performs a set of comprehensive convolution operations that mimics the overall function of the human visual system (HVS) via focusing on learning structural information in its input. The core of its computations is evaluating the components of the structural similarity metric (SSIM) in a setting that allows the kernels to learn to match structural information. The proposed SSIMLayer is inherently nonlinear and hence, it does not require subsequent nonlinear transformations. Experiments conducted on CIFAR-10 benchmark demonstrates that the SSIMLayer provides better convergence than the traditional convolutional layer, bypasses the need for nonlinear transformations and shows more robustness against noise perturbations and adversarial attacks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑