MobiAct: Efficient MAV Action Recognition Using MobileNetV4 with Contrastive Learning and Knowledge Distillation

TL;DR

MobiAct is a lightweight, efficient MAV action recognition framework that combines MobileNetV4, contrastive learning, and knowledge distillation to achieve high accuracy with low energy consumption and fast inference speed.

Contribution

This paper introduces MobiAct, a novel MAV action recognition model that integrates a lightweight backbone, a new knowledge distillation strategy, and attention mechanisms for improved efficiency and accuracy.

Findings

Achieves 92.12% accuracy on self-collected datasets.

Consumes only 136.16 pJ of energy per recognition.

Processes actions at 8.84 actions per second, twice as fast as leading methods.

Abstract

Accurate and efficient recognition of Micro Air Vehicle (MAV) motion is essential for enabling real-time perception and coordination in autonomous aerial swarm. However, most existing approaches rely on large, computationally intensive models that are unsuitable for resource-limited MAV platforms, which results in a trade-off between recognition accuracy and inference speed. To address these challenges, this paper proposes a lightweight MAV action recognition framework, MobiAct, designed to achieve high accuracy with low computational cost. Specifically, MobiAct adopts MobileNetV4 as the backbone network and introduces a Stage-wise Orthogonal Knowledge Distillation (SOKD) strategy to effectively transfer MAV motion features from a teacher network (ResNet18) to a student network, thereby enhancing knowledge transfer efficiency. Furthermore, a parameter-free attention mechanism is integrated into the architecture to improve recognition accuracy without increasing model complexity. In addition, a hybrid loss training strategy is developed to combine multiple loss objectives, which ensures stable and robust optimization during training. Experimental results demonstrate that the proposed MobiAct achieves low-energy and low-computation MAV action recognition, while maintaining the fastest action decoding speed among compared methods. Across all three self-collected datasets, MobiAct achieves an average recognition accuracy of 92.12%, while consuming only 136.16 pJ of energy and processing recognition at a rate of 8.84 actions per second. Notably, MobiAct decodes actions up to 2 times faster than the leading method, with highly comparable recognition accuracy, highlighting its superior efficiency in MAV action recognition.