Back to Search
Start Over
Mixture of deep networks for facial age estimation.
- Source :
-
Information Sciences . Sep2024, Vol. 679, pN.PAG-N.PAG. 1p. - Publication Year :
- 2024
-
Abstract
- In this paper, our objective is to simultaneously explore the learning of ordinal relationships among age labels and address the challenge of heterogeneous data resulting from the non-stationary aging process through an advanced mixture model of deep networks. Drawing upon the pivotal insight that the non-stationary aging process can be decomposed into a series of stationary subprocesses, we employ a divide-and-conquer strategy. This involves initially partitioning the age spectrum into multiple groups and subsequently training a specialized deep network, referred to as an "expert", for each distinct group. These experts are not functionally independent; instead, they are interconnected through specialized model designs and a joint training mechanism that consolidates them into a unified system. As a result, the learning of ordinal relationships is consistently maintained by solving the age-related tasks across the entire age label set. The final age estimation is accomplished through a hierarchical classification approach, leveraging the collective outputs from all the experts. Extensive experiments involving several well-known datasets for age estimation have demonstrated the superior performance of our proposed model over several existing state-of-the-art methods. • We propose a new deep mixture model that learns ordinal age relationships and handles the non-stationary aging process simultaneously. • Two well-designed visual tasks are proposed for ordinal relation learning and age estimation. • A sequential learning algorithm is proposed to make the mixture model trainable on machines with limited VRAM. • Our proposed mixture model outperforms several existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 00200255
- Volume :
- 679
- Database :
- Academic Search Index
- Journal :
- Information Sciences
- Publication Type :
- Periodical
- Accession number :
- 178423658
- Full Text :
- https://doi.org/10.1016/j.ins.2024.121086