Spectrum-Guided Adversarial Disparity Learning

Abstract

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.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
• Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
• Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
• Denoising Criterion for Variational Auto-Encoding Framework
• Adversarial Variational Embedding for Robust Semi-supervised Learning