Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition

TL;DR

This paper introduces Point Adversarial Self Mining (PASM), a simple method that enhances facial expression recognition by iteratively generating harder training samples through adversarial attacks and teacher-student guidance, improving accuracy.

Contribution

PASM is a novel approach that simulates human learning by adaptively generating challenging samples and leveraging teacher-student dynamics to boost recognition performance.

Findings

Outperforms existing state-of-the-art methods in facial expression recognition.

Effectively generates adaptive, harder training samples improving network robustness.

Iterative teacher-student updates lead to continuous performance gains.

Abstract

In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition. Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. The adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for facial expression recognition.