PoliTO-IIT-CINI提交EPIC-KITCHENS-100无监督领域自适应挑战赛动作识别
PoliTO-IIT-CINI 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）。其次，我们将这种方法扩展到处理未标记的目标数据，从而使模型能够以无监督的方式更简单地适应目标分布。为此，我们在我们的框架中包含了UDA算法，例如多级对抗对齐和注意熵。通过分析挑战设置，我们注意到在数据中存在二次并发偏移，这通常被称为环境偏差。它是由不同环境的存在造成的，即，厨房为了处理这两个转变（环境和时间），我们扩展了我们的系统，以执行多源多目标领域自适应。最后，我们在最终提案中采用了不同的模型，以利用流行视频架构的潜力，并为集成自适应引入了两个额外的损失。我们提交的作品（“plnet”条目）在排行榜上可见，“动词”排名第二，“名词”和“动作”排名第三。
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). Secondly, we extended this approach to work on unlabelled target data, enabling a simpler adaptation of the model to the target distribution in an unsupervised fashion. To this purpose, we included in our framework UDA algorithms, such as multi-level adversarial alignment and attentive entropy. By analyzing the challenge setting, we notice the presence of a secondary concurrence shift in the data, which is usually called environmental bias. It is caused by the existence of different environments, i.e., kitchens. To deal with these two shifts (environmental and temporal), we extended our system to perform Multi-Source Multi-Target Domain Adaptation. Finally, we employed distinct models in our final proposal to leverage the potential of popular video architectures, and we introduced two more losses for the ensemble adaptation. Our submission (entry 'plnet') is visible on the leaderboard and ranked in 2nd position for 'verb', and in 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。
