Within-network ensemble for face attributes classification

Ali Ahmed, Sara Atito and Yanıkoğlu, Berrin (2019) Within-network ensemble for face attributes classification. In: 20th International Conference on Image Analysis and Processing, ICIAP 2019, Trento, Italy

This is the latest version of this item.

Full text not available from this repository. (Request a copy)


Face attributes classification is drawing attention as a research topic with applications in multiple domains, such as video surveillance and social media analysis. In this work, we propose to train attributes in groups based on their localization (head, eyes, nose, cheek, mouth, shoulder, and general areas) in an end-to-end framework considering the correlations between the different attributes. Furthermore, a novel ensemble learning technique is introduced within the network itself that reduces the time of training compared to ensemble of several models. Our approach outperforms the state-of-the-art of the attributes with an average improvement of almost 0.60% and 0.48% points, on the public CELEBA and LFWA datasets, respectively.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: Deep learning; Ensemble learning; Face attributes classification; Multi-label classification; Multi-task learning
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 27 Jul 2023 11:22
Last Modified: 27 Jul 2023 11:22
URI: https://research.sabanciuniv.edu/id/eprint/46321

Available Versions of this Item

Actions (login required)

View Item
View Item