论文标题
频谱引导的对抗差异学习
Spectrum-Guided Adversarial Disparity Learning
论文作者
论文摘要
在活动识别领域中刻画类内差异是一个重大挑战，因为它需要对每个活动类别的主体特异性变异之间的相关性有良好的表示。在这项工作中，我们提出了一个新颖的端到端知识定向的对抗学习框架，该框架使用两个竞争性编码分布描绘了班级条件的阶级内差异，并通过降低学习的差距来学习纯化的潜在代码。此外，域知识以无监督的方式合并，以指导优化并进一步提高性能。四个HAR基准数据集上的实验证明了我们在一组最新的方法上提出的方法的鲁棒性和概括性。我们进一步证明了自动域知识在性能增强中的有效性。
It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class. In this work, we propose a novel end-to-end knowledge directed adversarial learning framework, which portrays the class-conditioned intraclass disparity using two competitive encoding distributions and learns the purified latent codes by denoising learned disparity. Furthermore, the domain knowledge is incorporated in an unsupervised manner to guide the optimization and further boosts the performance. The experiments on four HAR benchmark datasets demonstrate the robustness and generalization of our proposed methods over a set of state-of-the-art. We further prove the effectiveness of automatic domain knowledge incorporation in performance enhancement.
