Spectrum-Guided Adversarial Disparity Learning

TL;DR

This paper introduces a novel adversarial learning framework for activity recognition that effectively models intraclass disparity and incorporates domain knowledge to improve robustness and generalization across multiple datasets.

Contribution

It proposes a new end-to-end knowledge-guided adversarial learning method that captures class-specific intraclass disparity and integrates domain knowledge in an unsupervised manner.

Findings

Outperforms state-of-the-art on four HAR benchmark datasets.

Demonstrates robustness and generalization of the proposed method.

Shows effectiveness of automatic domain knowledge incorporation.

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.