论文标题
自动加入：通过Denoing AutoCododer和联合学习的有效的对抗训练，以进行无梯度的扰动以进行强大的操纵
AutoJoin: Efficient Adversarial Training against Gradient-Free Perturbations for Robust Maneuvering via Denoising Autoencoder and Joint Learning
论文作者
论文摘要
随着机器学习算法和普遍存在的传感器的日益增长，正在开发和部署许多“感知到控制”系统。为了确保他们的信任度，通过对抗训练改善其鲁棒性是一种潜在的方法。我们提出了一种名为AutoJoin的无梯度对抗训练技术，以有效，有效地为基于图像的机动生成可靠的模型。与对超过5M图像进行测试的其他最先进的方法相比，AutoJoin可实现显着的性能，可在40％的范围内对扰动提高范围，同时改善清洁性能高达300％。 AutoJoin的效率也很高，每个训练时期最多节省了86％的时间和90％的培训数据，而不是其他最先进的技术。自动加入的核心思想是在原始回归模型中使用解码器附件，在体系结构中创建一个DeNoising AutoCododer。这种体系结构允许共同学习任务“机动”和“ DeNoising传感器输入”，并互相加强彼此的性能。
With the growing use of machine learning algorithms and ubiquitous sensors, many `perception-to-control' systems are being developed and deployed. To ensure their trustworthiness, improving their robustness through adversarial training is one potential approach. We propose a gradient-free adversarial training technique, named AutoJoin, to effectively and efficiently produce robust models for image-based maneuvering. Compared to other state-of-the-art methods with testing on over 5M images, AutoJoin achieves significant performance increases up to the 40% range against perturbations while improving on clean performance up to 300%. AutoJoin is also highly efficient, saving up to 86% time per training epoch and 90% training data over other state-of-the-art techniques. The core idea of AutoJoin is to use a decoder attachment to the original regression model creating a denoising autoencoder within the architecture. This architecture allows the tasks `maneuvering' and `denoising sensor input' to be jointly learnt and reinforce each other's performance.
