Abstract
Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected in the literature, exposing these solutions to important performance degradation. In this work, we tackle this issue by introducing, for the first time, an approach for Unsupervised Domain Adaptation (UDA) in sparse TAL, which we refer to as Semantic Adversarial unsupervised Domain Adaptation (SADA). Our contribution is threefold: (1) we pioneer the development of a domain adaptation model that operates on realistic sparse action detection benchmarks; (2) we tackle the limitations of global-distribution alignment techniques by introducing a novel adversarial loss that is sensitive to local class distributions, ensuring finer-grained adaptation; and (3) we present a novel experimental setup, based on EpicKitchens100, that evaluates multiple types of domain shifts in a comprehensive manner. Our experimental results indicate that SADA improves the adaptation across domains when compared to fully supervised state-of-the-art and alternative UDA methods, attaining a relative performance boost of up to 14%.
Abstract (translated)
Temporal Action Localization(TAL)是一个复杂的任务,在尝试在现实应用中泛化到新的——未见过的——领域时,会提出相关的挑战。尽管这些场景在文献中很现实,但通常被忽视,这使得这些解决方案在重要性能降级方面面临风险。在这项工作中,我们通过引入在稀疏TAL中进行无监督领域适应(UDA)的方法,我们称之为语义对抗无监督领域适应(SADA),来解决这一问题。我们的贡献是三方面的:(1)我们首创了一个在现实稀疏动作检测基准上运行的领域适应模型;(2)我们引入了一种新的对抗损失,对局部类别分布敏感,确保了更细粒度的适应;(3)我们基于EpicKitchens100构建了一个新的实验设置,以全面评估各种领域转移。我们的实验结果表明,与完全监督最先进的和替代UDA方法相比,SADA在领域泛化方面具有显著的提高,实现了相对性能提升至14%。
URL
https://arxiv.org/abs/2312.13377