Spectrum-Guided Adversarial Disparity Learning

View/ Open
File version
Accepted Manuscript (AM)
Author(s)
Liu, Z
Yao, L
Bai, L
Wang, X
Wang, C
Griffith University Author(s)
Year published
2020
Metadata
Show full item recordAbstract
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 ...
View more >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.
View less >
View more >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.
View less >
Conference Title
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Copyright Statement
© ACM, 2020. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ISBN: 978-1-4503-7998-4, https://doi.org/10.1145/3394486.3403054
Subject
Artificial intelligence