Active Adversarial Domain Adaptationdoi:10.1109/WACV45572.2020.9093390Jong-Chyi SuYi-Hsuan TsaiKihyuk SohnBuyu LiuSubhransu MajiManmohan ChandrakerIEEEWorkshop on Applications of Computer Vision
由于半监督学习展示出了优异的性能,在标签不足的情况下,如果能将主动学习与半监督学习结合,将会取得更优异的性能。 【Semi-Supervised Active Learning for Semi-Supervised Models: Exploit Adversarial Examples With Graph-Based Virtual Labels】—https://openaccess.thecvf.com/content/ICCV2021/html/Guo_Semi-Supe...
(PADA)Partial Adversarial Domain Adaptation笔记 提出了部分对抗性领域自适应算法(PADA),它通过降低离群源类别数据的权重来减轻负迁移,并通过匹配共享标签空间中的特征分布来促进正迁移。 Partial Adversarial Domain Adaptation: ,且 源域:,个类别 目标域:,个类别 挑战: 降低离群源类的影响来缓解负迁移 减少的分布...
S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation Active Universal D...
Variational Adversarial Active Learning https://arxiv.org/abs/1904.00370 六、应用场景 由于主动学习解决的是如何从无标签数据中选择价值高的样本进行标注,所以在数据标签难以获得、标注成本大的场景和实际问题中被广泛应用。 互联网大数据相关的应用:在互联网的大数据场景中,无标签的数据不计其数,但是又不可能把所有...
【Variational Adversarial Active Learning】—https://arxiv.org/abs/1904.00370 5. 应用场景 由于主动学习解决的是如何从无标签数据中选择价值高的样本进行标注,所以在数据标签难以获得、标注成本大的场景和实际问题中被广泛应用。 互联网大数据相关的应用:在互联网的大数据场景中,无标签的数据不计其数,但是又不可能...
Variational Adversarial Active Learning https://arxiv.org/abs/1904.00370 应用场景 由于主动学习解决的是如何从无标签数据中选择价值高的样本进行标注,所以在数据标签难以获得、标注成本大的场景和实际问题中被广泛应用。 互联网大数据相关的应用:在互联网的大数据场景中,无标签的数据不计其数,但是又不可能把所有的数...
Adversarial sampling for active learning. In Proceedings of the IEEE/CVF Win- ter Conference on Applications of Computer Vision, pages 3071–3079, 2020. [57] Sudhanshu Mittal, Maxim Tatarchenko, and Thomas Brox. Semi-supervised semantic segmentation with high-and low- lev...
feature space. However, the performance of this method is critically restricted by the data category in the datasets. To address this, Sinha et al.27instead employ an adversarial approach to diversity-based sample query, which selects the unlabeled data based on the discriminator’s output, ...
This framework is based on an adversarial domain adaptation approach that extracts domain-invariant feature representations of data from different buildings. The feature extraction function is trained in an adversarial way, which ensures that the extracted feature distributions are robust to changes in ...