Analysis of Semi-Supervised Methods for Facial Expression Recognition

Etemad, Ali

doi:10.1109/acii55700.2022.9953876

Cited by 8 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many SSL models have presented excellent performance in computer vision and machine learning [28], [29], and they can be categorized into two broad categories: pseudo-labeling [30] and consistency regularization [31], [32]. For a systematic review of SSL in FER, please refer to [33].…”

Section: B Deep Learning-based Semi-supervised Learningmentioning

confidence: 99%

Rethinking Pseudo-Labeling for Semi-Supervised Facial Expression Recognition With Contrastive Self-Supervised Learning

Fang

Han

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Self-supervised learning for semi-supervised facial expression recognition aims to avoid the need to collect expensive labeled facial expression data. Existing methods demonstrate an impressive performance boost, but they artificially assume that small labeled facial expression data and large unlabeled facial expression data are from the same class distribution. In a more realistic scenario, when utilizing facial expression data from a large face recognition database as unlabeled data, there will be a mismatch distribution between the two sets of data. This often results in severe performance degradation due to incorrect propagation of unlabeled data from unrelated sources. In this paper, we address the class distribution mismatch problem in deep semi-supervised learning-based facial expression recognition. Specifically, we propose a silhouette coefficient-based contrast clustering algorithm, which determines the degree of separation between clusters by examining the intra-cluster and inter-cluster distances to accurately detect out-of-distribution data. In addition, we propose a pseudo-labeling rethinking strategy that matches the soft pseudo-labels estimated from a fine-tuned network to the contrast clustering to produce reliable pseudolabels. Experiments on three in-the-wild datasets, RAF-DB, FERPlus and AffectNet, demonstrate the effectiveness of our method, and our approach performs well compared to state-of-the-art methods.INDEX TERMS Facial expression recognition, semi-supervised learning, contrastive self-supervised learning, out-of-distribution data.

show abstract

Section: B Deep Learning-based Semi-supervised Learningmentioning

confidence: 99%

Rethinking Pseudo-Labeling for Semi-Supervised Facial Expression Recognition With Contrastive Self-Supervised Learning

Fang

Han

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For the Chrome Reviews dataset, the maximum length of the processed text is set to 80 words based on the sample detail information in the database as well as the hardware processing capability. The train batch size is set to 32 for labelled samples and 16 for samples with pseudo labels [44,45]. The Adam optimizer is implemented.…”

Section: Training Detailsmentioning

confidence: 99%

A semi-supervised short text sentiment classification method based on improved Bert model from unlabelled data

Zou

Wang

2023

J Big Data

View full text Add to dashboard Cite

Short text information has considerable commercial value and immeasurable social value. Natural language processing and short text sentiment analysis technology can organize and analyze short text information on the Internet. Natural language processing tasks such as sentiment classification have achieved satisfactory performance under a supervised learning framework. However, traditional supervised learning relies on large-scale and high-quality manual labels and obtaining high-quality label data costs a lot. Therefore, the strong dependence on label data hinders the application of the deep learning model to a large extent, which is the bottleneck of supervised learning. At the same time, short text datasets such as product reviews have an imbalance in the distribution of data samples. To solve the above problems, this paper proposes a method to predict label data according to semi-supervised learning mode and implements the MixMatchNL data enhancement method. Meanwhile, the Bert pre-training model is updated. The cross-entropy loss function in the model is improved to the Focal Loss function to alleviate the data imbalance in short text datasets. Experimental results based on public datasets indicate the proposed model has improved the accuracy of short text sentiment recognition compared with the previous update and other state-of-the-art models.

show abstract

“…Facial Landmark in FER: The purpose of facial landmark detection is to identify the location of distinguishable key points on a human face. Currently, with the combination of facial landmark detection and deep learning techniques, such as face recognition [15,20], facial expression recognition [13,31], and face tracking [17], great progress has been made in the application of facial landmark detection, which has also facilitated the research of many accurate facial landmark detectors. Many accurate and widely used facial landmark detectors have been proposed, such as [4,11,14,45].…”

Section: Deep Learning and Attention In Fermentioning

confidence: 99%

“…Automatic analysis techniques for facial expressions are being used in more and more fields, such as medical care, driver fatigue, robot interaction, and student classroom state analysis [3][4][5][6][7]. The changing needs have also given rise to many problems in different scenarios, and in the past period, the algorithms have been iterated continuously in FER-related problems [8][9][10][11][12][13][14][15][16][17][18], and eventually, these algorithms have achieved good results. Meanwhile, in order to meet the requirements of different experiments, some datasets have been generated, such as CK+ [19], FER2013 [20], FERPLUS [21], etc.…”

Section: Introductionmentioning

confidence: 99%

Facial Expression Recognition Using Dual Path Feature Fusion and Stacked Attention

Zhu

et al. 2022

Future Internet

View full text Add to dashboard Cite

Facial Expression Recognition (FER) can achieve an understanding of the emotional changes of a specific target group. The relatively small dataset related to facial expression recognition and the lack of a high accuracy of expression recognition are both a challenge for researchers. In recent years, with the rapid development of computer technology, especially the great progress of deep learning, more and more convolutional neural networks have been developed for FER research. Most of the convolutional neural performances are not good enough when dealing with the problems of overfitting from too-small datasets and noise, due to expression-independent intra-class differences. In this paper, we propose a Dual Path Stacked Attention Network (DPSAN) to better cope with the above challenges. Firstly, the features of key regions in faces are extracted using segmentation, and irrelevant regions are ignored, which effectively suppresses intra-class differences. Secondly, by providing the global image and segmented local image regions as training data for the integrated dual path model, the overfitting problem of the deep network due to a lack of data can be effectively mitigated. Finally, this paper also designs a stacked attention module to weight the fused feature maps according to the importance of each part for expression recognition. For the cropping scheme, this paper chooses to adopt a cropping method based on the fixed four regions of the face image, to segment out the key image regions and to ignore the irrelevant regions, so as to improve the efficiency of the algorithm computation. The experimental results on the public datasets, CK+ and FERPLUS, demonstrate the effectiveness of DPSAN, and its accuracy reaches the level of current state-of-the-art methods on both CK+ and FERPLUS, with 93.2% and 87.63% accuracy on the CK+ dataset and FERPLUS dataset, respectively.

show abstract

Analysis of Semi-Supervised Methods for Facial Expression Recognition

Cited by 8 publications

References 18 publications

Rethinking Pseudo-Labeling for Semi-Supervised Facial Expression Recognition With Contrastive Self-Supervised Learning

Rethinking Pseudo-Labeling for Semi-Supervised Facial Expression Recognition With Contrastive Self-Supervised Learning

A semi-supervised short text sentiment classification method based on improved Bert model from unlabelled data

Facial Expression Recognition Using Dual Path Feature Fusion and Stacked Attention

Contact Info

Product

Resources

About