Efficient Facial Landmark Detection for Embedded Systems

TL;DR

This paper presents EFLD, a lightweight and robust facial landmark detection model optimized for embedded systems, achieving high accuracy with low power consumption and latency through innovative design and training strategies.

Contribution

The paper introduces a novel efficient facial landmark detection model with a cross-format training strategy, significantly improving robustness and efficiency on resource-constrained devices.

Findings

Outperforms competitors in IEEE ICME 2024 Grand Challenges PAIR Competition

Reduces computational demands and model size

Enhances accuracy and robustness without increasing inference costs

Abstract

This paper introduces the Efficient Facial Landmark Detection (EFLD) model, specifically designed for edge devices confronted with the challenges related to power consumption and time latency. EFLD features a lightweight backbone and a flexible detection head, each significantly enhancing operational efficiency on resource-constrained devices. To improve the model's robustness, we propose a cross-format training strategy. This strategy leverages a wide variety of publicly accessible datasets to enhance the model's generalizability and robustness, without increasing inference costs. Our ablation study highlights the significant impact of each component on reducing computational demands, model size, and improving accuracy. EFLD demonstrates superior performance compared to competitors in the IEEE ICME 2024 Grand Challenges PAIR Competition, a contest focused on low-power, efficient, and accurate facial-landmark detection for embedded systems, showcasing its effectiveness in real-world facial landmark detection tasks.