PoliTO-IIT提交EPIC-KITCHENS-100无监督领域自适应挑战赛动作识别
PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
摘要：
在本报告中，我们描述了我们提交EPIC-Kitchen-100无监督领域自适应（UDA）行动识别挑战赛的技术细节。为了解决在UDA设置下存在的域转移，我们首先利用了最近的领域泛化（DG）技术，称为相对范数对齐（RNA）。它包括设计一个能够很好地推广到任何看不见的领域的模型，而不管在训练时访问目标数据的可能性。然后，在第二阶段，我们将该方法扩展到处理未标记的目标数据，使模型能够以无监督的方式适应目标分布。为此，我们在我们的框架中包括现有的UDA算法，如时间注意对抗适应网络（TA 3 N），以及新的多流一致性损失，即时间硬范数对齐（T-HNA）和最小熵一致性（MEC）。我们提交的作品（“plnet”条目）在排行榜上可见，它获得了“动词”的第一名，以及“名词”和“动作”的第三名。
英文摘要：
In this report, we describe the technical details of our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition. To tackle the domain-shift which exists under the UDA setting, we first exploited a recent Domain Generalization (DG) technique, called Relative Norm Alignment (RNA). It consists in designing a model able to generalize well to any unseen domain, regardless of the possibility to access target data at training time. Then, in a second phase, we extended the approach to work on unlabelled target data, allowing the model to adapt to the target distribution in an unsupervised fashion. For this purpose, we included in our framework existing UDA algorithms, such as Temporal Attentive Adversarial Adaptation Network (TA3N), jointly with new multi-stream consistency losses, namely Temporal Hard Norm Alignment (T-HNA) and Min-Entropy Consistency (MEC). Our submission (entry 'plnet') is visible on the leaderboard and it achieved the 1st position for 'verb', and the 3rd position for both 'noun' and 'action'.
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。
