当前位置: X-MOL 学术IEEE Trans. Image 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.)
Improved Techniques for Adversarial Discriminative Domain Adaptation.
IEEE Transactions on Image Processing ( IF 10.8 ) Pub Date : 2019-11-06 , DOI: 10.1109/tip.2019.2950768
Aaron Chadha , Yiannis Andreopoulos

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available for the target domain. While ADDA has already achieved better training efficiency and competitive accuracy on image classification in comparison to other adversarial based methods, we investigate whether we can improve its performance with a new framework and new loss formulations. Following the framework of semi-supervised GANs, we first extend the discriminator output over the source classes, in order to model the joint distribution over domain and task. We thus leverage on the distribution over the source encoder posteriors (which is fixed during adversarial training) and propose maximum mean discrepancy (MMD) and reconstruction-based loss functions for aligning the target encoder distribution to the source domain. We compare and provide a comprehensive analysis of how our framework and loss formulations extend over simple multi-class extensions of ADDA and other discriminative variants of semi-supervised GANs. In addition, we introduce various forms of regularization for stabilizing training, including treating the discriminator as a denoising autoencoder and regularizing the target encoder with source examples to reduce overfitting under a contraction mapping (i.e., when the target per-class distributions are contracting during alignment with the source). Finally, we validate our framework on standard datasets like MNIST, USPS, SVHN, MNIST-M and Office-31. We additionally examine how the proposed framework benefits recognition problems based on sensing modalities that lack training data. This is realized by introducing and evaluating on a neuromorphic vision sensing (NVS) sign language recognition dataset, where the source domain constitutes emulated neuromorphic spike events converted from conventional pixel-based video and the target domain is experimental (real) spike events from an NVS camera. Our results on all datasets show that our proposal is both simple and efficient, as it competes or outperforms the state-of-the-art in unsupervised domain adaptation, such as DIFA and MCDDA, whilst offering lower complexity than other recent adversarial methods.

中文翻译:


对抗性判别域适应的改进技术。



对抗性判别域适应(ADDA)是图像分类中无监督域适应的有效框架,其中假设源域和目标域具有相同的类,但目标域没有可用的标签。虽然与其他基于对抗性的方法相比,ADDA 已经在图像分类方面实现了更好的训练效率和竞争准确性,但我们研究是否可以通过新的框架和新的损失公式来提高其性能。遵循半监督 GAN 的框架,我们首先将判别器输出扩展到源类上,以便对域和任务上的联合分布进行建模。因此,我们利用源编码器后验分布(在对抗训练期间固定)并提出最大平均差异(MMD)和基于重建的损失函数,以将目标编码器分布与源域对齐。我们对我们的框架和损失公式如何扩展到 ADDA 的简单多类扩展和半监督 GAN 的其他判别变体进行比较并提供全面的分析。此外,我们引入了各种形式的正则化来稳定训练,包括将鉴别器视为去噪自动编码器,并使用源示例对目标编码器进行正则化,以减少收缩映射下的过度拟合(即,当目标每类分布在对齐期间收缩时)与来源)。最后,我们在 MNIST、USPS、SVHN、MNIST-M 和 Office-31 等标准数据集上验证我们的框架。我们还研究了所提出的框架如何有利于基于缺乏训练数据的传感方式的识别问题。 这是通过引入和评估神经形态视觉感知 (NVS) 手语识别数据集来实现的,其中源域构成从传统基于像素的视频转换而来的模拟神经形态尖峰事件,目标域是来自 NVS 的实验(真实)尖峰事件相机。我们在所有数据集上的结果表明,我们的建议既简单又有效,因为它在无监督领域适应方面竞争或优于最先进的技术,例如 DIFA 和 MCDDA,同时提供比其他最近的对抗方法更低的复杂性。
更新日期:2020-04-22
down
wechat
bug