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

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.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Distilling the Knowledge in a Neural Network
• Deep Facial Expression Recognition: A Survey
• Going Deeper in Facial Expression Recognition using Deep Neural Networks
• Fast is better than free: Revisiting adversarial training
• A Deeper Look at Facial Expression Dataset Bias
• A Deep Learning Perspective on the Origin of Facial Expressions
• Adversarial Training against Location-Optimized Adversarial Patches
• Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
• Face Hallucination with Finishing Touches
• Probabilistic Attribute Tree in Convolutional Neural Networks for Facial Expression Recognition
• Pose-adaptive Hierarchical Attention Network for Facial Expression Recognition
• Occlusion-Adaptive Deep Network for Robust Facial Expression Recognition