Spectrum-Guided Adversarial Disparity Learning
This work addresses the problem of accurately representing intraclass disparity in activity recognition, which is incremental as it builds on existing adversarial learning methods with domain knowledge incorporation.
The paper tackles the challenge of precisely portraying intraclass disparity in activity recognition by proposing a novel end-to-end knowledge-directed adversarial learning framework that learns purified latent codes by denoising learned disparity, achieving robustness and generalization demonstrated on four HAR benchmark datasets.
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.