AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search
It addresses the need for generic, high-performing GCN architectures in HAR, which is incremental as it builds on existing NAS and GCN techniques.
This paper tackled the problem of limited applicability of dataset-specific Graph Convolution Networks (GCNs) in Human Activity Recognition (HAR) by introducing AutoGCN, a Neural Architecture Search (NAS) algorithm that outperformed conventional NAS, GCN methods, and random search on two large-scale skeleton-based action recognition datasets.
This paper introduces AutoGCN, a generic Neural Architecture Search (NAS) algorithm for Human Activity Recognition (HAR) using Graph Convolution Networks (GCNs). HAR has gained attention due to advances in deep learning, increased data availability, and enhanced computational capabilities. At the same time, GCNs have shown promising results in modeling relationships between body key points in a skeletal graph. While domain experts often craft dataset-specific GCN-based methods, their applicability beyond this specific context is severely limited. AutoGCN seeks to address this limitation by simultaneously searching for the ideal hyperparameters and architecture combination within a versatile search space using a reinforcement controller while balancing optimal exploration and exploitation behavior with a knowledge reservoir during the search process. We conduct extensive experiments on two large-scale datasets focused on skeleton-based action recognition to assess the proposed algorithm's performance. Our experimental results underscore the effectiveness of AutoGCN in constructing optimal GCN architectures for HAR, outperforming conventional NAS and GCN methods, as well as random search. These findings highlight the significance of a diverse search space and an expressive input representation to enhance the network performance and generalizability.