arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.02067cs.CV
收藏

基于距离的超球面分类多源开集领域自适应

Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation

Politecnico di Torino(都灵理工大学);Italian Institute of Technology(意大利技术研究院)

Silvia Bucci, Francesco Cappio Borlino, Barbara Caputo, Tatiana Tommasi

摘要:

在封闭世界场景中训练的视觉系统在部署时遇到新的环境条件、新的数据分布和新的类别时会失败。如何走向开放世界学习是一个长期存在的研究问题。现有的解决方案主要集中在问题的特定方面(单域开集,多域闭集),或提出复杂的策略,结合几个损失和手动调整超参数。在这项工作中,我们通过引入HyMOS来解决多源开放集领域自适应:一个简单的模型,利用对比学习的力量及其超球面特征空间的属性来正确预测目标上的已知标签,同时拒绝属于任何未知类的样本。HyMOS在对比学习的实例转换中包含风格迁移,以获得领域不变性,同时避免负迁移的风险。根据观察到的数据分布定义自定进度的阈值,并在训练期间在线更新,从而允许处理已知-未知分离。我们在三个具有挑战性的数据集上验证了我们的方法。所获得的结果表明,HyMOS优于几个竞争对手,定义了新的国家的最先进的。https://github.com/silvia1993/HyMOS

英文摘要:

Vision systems trained in closed-world scenarios fail when presented with new environmental conditions, new data distributions, and novel classes at deployment time. How to move towards open-world learning is a long-standing research question. The existing solutions mainly focus on specific aspects of the problem (single domain Open-Set, multi-domain Closed-Set), or propose complex strategies which combine several losses and manually tuned hyperparameters. In this work, we tackle multi-source Open-Set domain adaptation by introducing HyMOS: a straightforward model that exploits the power of contrastive learning and the properties of its hyperspherical feature space to correctly predict known labels on the target, while rejecting samples belonging to any unknown class. HyMOS includes style transfer among the instance transformations of contrastive learning to get domain invariance while avoiding the risk of negative-transfer. A self-paced threshold is defined on the basis of the observed data distribution and updates online during training, allowing to handle the known-unknown separation. We validate our method over three challenging datasets. The obtained results show that HyMOS outperforms several competitors, defining the new state-of-the-art. Our code is available at https://github.com/silvia1993/HyMOS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑