One-Frame Calibration with Siamese Network in Facial Action Unit Recognition

TL;DR

This paper introduces a one-frame calibration approach using a Siamese network for facial action unit recognition, significantly improving accuracy by reducing facial attribute biases from a single neutral reference image.

Contribution

It proposes a novel one-frame calibration method with a Calibrating Siamese Network that enhances AU recognition accuracy across diverse facial attributes.

Findings

Substantially improves AU recognition performance.

Outperforms naive baseline subtraction and fine-tuned methods.

Achieves state-of-the-art results on multiple datasets.

Abstract

Automatic facial action unit (AU) recognition is used widely in facial expression analysis. Most existing AU recognition systems aim for cross-participant non-calibrated generalization (NCG) to unseen faces without further calibration. However, due to the diversity of facial attributes across different identities, accurately inferring AU activation from single images of an unseen face is sometimes infeasible, even for human experts -- it is crucial to first understand how the face appears in its neutral expression, or significant bias may be incurred. Therefore, we propose to perform one-frame calibration (OFC) in AU recognition: for each face, a single image of its neutral expression is used as the reference image for calibration. With this strategy, we develop a Calibrating Siamese Network (CSN) for AU recognition and demonstrate its remarkable effectiveness with a simple iResNet-50 (IR50) backbone. On the DISFA, DISFA+, and UNBC-McMaster datasets, we show that our OFC CSN-IR50 model (a) substantially improves the performance of IR50 by mitigating facial attribute biases (including biases due to wrinkles, eyebrow positions, facial hair, etc.), (b) substantially outperforms the naive OFC method of baseline subtraction as well as (c) a fine-tuned version of this naive OFC method, and (d) also outperforms state-of-the-art NCG models for both AU intensity estimation and AU detection.