• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >Robust adversarial discriminative domain adaptation for real-world cross-domain visual recognition
【24h】

Robust adversarial discriminative domain adaptation for real-world cross-domain visual recognition

机译：真正的对抗歧视域适应真实世界跨域视觉识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

Deep convolutional networks (CNNs) are able to learn robust representations and empower many computer vision tasks such as object recognition. However, when applying CNNs to industrial visual systems, they usually suffer from domain shift that exists between the training data and testing data. Such shift can be caused by different environment, types of cameras and exteriors of objects, leading to degrading performance and hindering the practical applications of CNNs in real-world visual recognition. To tackle this problem, Adversarial domain adaptation (ADA) reduces such shift by min-max optimization. However, current CNNs with ADA are hard to train due to training instability of adversarial network. In this paper, we propose a unified and easy-to-train domain adaptation framework, namely Attention-based Domain-confused Adversarial Domain ADaptation (AD3). Our method leverages both adversarial and statistical domain alignment, allows flexibility for source and target feature extractors and simultaneously performs feature-level and attention-level alignment. The statistical domain alignment promotes and stabilizes the adversarial domain learning, which reduces the manual work of tuning the hyper-parameters. The experimental results validate that our method performs better adaptation and faster convergence for adversarial domain learning than existing state-of-the-art methods on DIGITS, Office-31 and VisDA domain adaptation benchmarks. (C) 2020 Elsevier B.V. All rights reserved.
机译：深度卷积网络（CNNS）能够学习强大的表示，并授权许多计算机视觉任务，例如对象识别。但是，在将CNN应用于工业视觉系统时，它们通常遭受训练数据和测试数据之间存在的域移位。这种转变可以由不同的环境，摄像机类型和物体的外部引起，导致性能下降并阻碍CNNS在真实的视觉识别中的实际应用。为了解决这个问题，对抗域适应（ADA）通过最小最大优化降低了这种偏移。然而，由于对抗性网络的培训不稳定，与ADA的当前CNN难以训练。在本文中，我们提出了一个统一且易于列车的域适应框架，即关注的域 - 混淆的对抗域适应（AD3）。我们的方法利用了对抗和统计域对齐，允许灵活性用于源和目标特征提取器，并同时执行特征级和注意力级别对齐。统计域对齐促进并稳定对抗域学习，这减少了调整超参数的手工工作。实验结果验证了我们的方法对对抗域学习的更好的适应和更快的收敛性，而不是在数字，Office-31和Visda域适应基准上的现有最先进的方法。 （c）2020 Elsevier B.v.保留所有权利。

著录项

获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号