Published on Mon Dec 17 2018

Probabilistic Attribute Tree in Convolutional Neural Networks for Facial Expression Recognition

Jie Cai, Zibo Meng, Ahmed Shehab Khan, Zhiyuan Li, James O'Reilly, Yan Tong

The Probabilistic Attribute Tree-CNN (PAT-CNN) explicitly deals with the large intra-class variations caused by attributes, e.g., age, race, and gender. The PAT-CNN achieves the best performance using a single model on the SFEW dataset.

0
0
0
Abstract

In this paper, we proposed a novel Probabilistic Attribute Tree-CNN (PAT-CNN) to explicitly deal with the large intra-class variations caused by identity-related attributes, e.g., age, race, and gender. Specifically, a novel PAT module with an associated PAT loss was proposed to learn features in a hierarchical tree structure organized according to attributes, where the final features are less affected by the attributes. Then, expression-related features are extracted from leaf nodes. Samples are probabilistically assigned to tree nodes at different levels such that expression-related features can be learned from all samples weighted by probabilities. We further proposed a semi-supervised strategy to learn the PAT-CNN from limited attribute-annotated samples to make the best use of available data. Experimental results on five facial expression datasets have demonstrated that the proposed PAT-CNN outperforms the baseline models by explicitly modeling attributes. More impressively, the PAT-CNN using a single model achieves the best performance for faces in the wild on the SFEW dataset, compared with the state-of-the-art methods using an ensemble of hundreds of CNNs.

Thu Apr 25 2019
Computer Vision
A Deeper Look at Facial Expression Dataset Bias
The Emotion-Conditional Adaption Network (ECAN) can learn domain-invariant and discriminative feature representations. It can match both the marginal and the conditional distributions across domains simultaneously. ECAN can yield competitive performances across various facial expression transfer tasks.
0
0
0
Mon Jul 20 2020
Computer Vision
Investigating Bias and Fairness in Facial Expression Recognition
Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision. However, virtually none of these datasets have been acquired with consideration of fair distribution across the human population.
0
0
0
Tue Jun 08 2021
Computer Vision
MViT: Mask Vision Transformer for Facial Expression Recognition in the wild
Facial Expression Recognition (FER) in the wild is an extremely challenging task in computer vision. The self-attention mechanism makes transformers obtain a global receptive field in the first layer. This dramatically enhances the feature extraction capability of transformers.
0
0
0
Mon Feb 04 2019
Computer Vision
Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network
Facial expression recognition has been an active research area over the past decades. Traditional approaches for this problem rely on hand-crafted features and a classifier trained on a database of images or videos. In this work, we propose a deep learning approach based on attentional convolutional network.
0
0
0
Thu Apr 01 2021
Computer Vision
Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition
0
0
0
Thu Aug 19 2021
Computer Vision
Understanding and Mitigating Annotation Bias in Facial Expression Recognition
The performance of a computer vision model depends on the size and quality of training data. We demonstrate that many expression datasets contain significant annotation biases between genders. We propose an AU-Calibrated Facial Expression Recognition framework that incorporates the triplet loss into the objective function.
0
0
0