.png){kind=icon}
Return
Timid semi-supervised learning for face expression analysis
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109417.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the last years, semi-supervised learning has been proposed as a strategy with high potential for im-proving machine learning capabilities. Face expression recognition may highly benefit from such a tech-nique, as accurate labeling is both difficult and costly, whereas millions of unlabeled images with human faces are available on the Internet, but without annotations. In this paper we evaluate the benefits of semi-supervised learning in the practical scenarios of face expression analysis. Our conclusion is that better performance is indeed achievable, but by methods that put a distinct emphasis on the diversity of exploring patterns in the unlabeled data domain. The evaluation is carried on multiple tasks such as detecting Action Units on EmotioNet, assessing Action Units intensity on the spontaneous DISFA database and, respectively, recognizing expressions on static images acquired in the wild, from the RAF-DB and FER+ databases. We show that, in these scenarios, a so-called timid semi-supervised learner is more robust and achieves higher performance than standard, confident semi-supervised learners.(c) 2023 Elsevier Ltd. All rights reserved.
Keywords:
Face expression
Action units
Semi-supervised learning
Diversity
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSaveShareSave
ShareSaveChiral eighteen-component three-dimensional supramolecular entities stabilized by the hydrogen bonding and coordination interactions.png)
Tetrahedron
TetrahedronIF0
PREAI
ShareSaveOrthogonal channel attention-based multi-task learning for multi-view facial expression recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveImproving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-mapPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveFast algorithms for incremental and decremental semi-supervised discriminant analysisPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave
View more