A Novel Multi-task Tensor Correlation Neural Network for Facial Attribute Prediction
Authors:
Open Access
- 13 November 2020
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 12 (1) , 1-22
Abstract
Multi-task learning plays an important role in face multi-attribute prediction. At present, most researches excavate the shared information between attributes by sharing all convolutional layers. However, it is not appropriate to treat the low-level and high-level features of the face multi-attribute equally, because the high-level features are more biased toward the specific content of the category. In this article, a novel multi-attribute tensor correlation neural network (MTCN) is used to predict face attributes. MTCN shares all attribute features at the low-level layers, and then distinguishes each attribute feature at the high-level layers. To better excavate the correlations among high-level attribute features, each sub-network explores useful information from other networks to enhance its original information. Then a tensor canonical correlation analysis method is used to seek the correlations among the highest-level attributes, which enhances the original information of each attribute. After that, these features are mapped into a highly correlated space through the correlation matrix. Finally, we use sufficient experiments to verify the performance of MTCN on the CelebA and LFWA datasets and our MTCN achieves the best performance compared with the latest multi-attribute recognition algorithms under the same settings.Keywords
All Related Versions
Funding Information
- Cooperation and Exchange Program (61661146006)
- National Key R8D Program of China (2016YT80201900)
- National Natural Science Foundation of China (61902119, 61625202)
- China Postdoctoral Science Foundation (2019M652758 and 2019TQ0087)
- Hong Kong Scholars Program (XJ2020032)
This publication has 44 references indexed in Scilit:
- Local Structure-Based Sparse Representation for Face RecognitionACM Transactions on Intelligent Systems and Technology, 2015
- Age Estimation via Grouping and Decision FusionIEEE Transactions on Information Forensics and Security, 2015
- Tensor Canonical Correlation Analysis for Multi-View Dimension ReductionIEEE Transactions on Knowledge and Data Engineering, 2015
- A framework for joint estimation of age, gender and ethnicity on a large databaseImage and Vision Computing, 2014
- Learning Race from Face: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- FaceTracer: A Search Engine for Large Collections of Images with Faces2008
- Canonical Correlation Analysis: An Overview with Application to Learning MethodsNeural Computation, 2004
- On the Best Rank-1 and Rank-(R1 ,R2 ,. . .,RN) Approximation of Higher-Order TensorsSIAM Journal on Matrix Analysis and Applications, 2000
- Principal Component Analysis of Three-Mode Data by Means of Alternating Least Squares AlgorithmsPsychometrika, 1980
- Analysis of Individual Differences in Multidimensional Scaling Via an N-way Generalization of “Eckart-Young” DecompositionPsychometrika, 1970