论文标题
特征空间中的虚拟对手训练以改善无监督的视频域适应
Virtual Adversarial Training in Feature Space to Improve Unsupervised Video Domain Adaptation
论文作者
论文摘要
虚拟的对抗训练最近在半监督学习以及无监督的领域适应中取得了很大的成功。但是，到目前为止，它已用于像素空间中的输入样品，而我们建议将其直接应用于特征矢量。我们还讨论了熵最小化和决策 - 决策迭代的精致培训的不稳定行为，并与域适应性的老师进行了建议，并建议实现相似行为的替代品。通过将上述技术添加到最先进的模型TA $^3 $ N中，我们要么保持竞争性结果，要么在多个无监督的视频域适应任务中胜过先前的艺术
Virtual Adversarial Training has recently seen a lot of success in semi-supervised learning, as well as unsupervised Domain Adaptation. However, so far it has been used on input samples in the pixel space, whereas we propose to apply it directly to feature vectors. We also discuss the unstable behaviour of entropy minimization and Decision-Boundary Iterative Refinement Training With a Teacher in Domain Adaptation, and suggest substitutes that achieve similar behaviour. By adding the aforementioned techniques to the state of the art model TA$^3$N, we either maintain competitive results or outperform prior art in multiple unsupervised video Domain Adaptation tasks
