Learning Deep Representation for Face Alignment with Auxiliary Attributes
Publication in refereed journal

Times Cited
Web of Science135WOS source URL (as at 01/07/2020) Click here for the latest count
Altmetrics Information

Other information
AbstractIn this study, we show that landmark detection or face alignment task is not a single and independent problem. Instead, its robustness can be greatly improved with auxiliary information. Specifically, we jointly optimize landmark detection together with the recognition of heterogeneous but subtly correlated facial attributes, such as gender, expression, and appearance attributes. This is non-trivial since different attribute inference tasks have different learning difficulties and convergence rates. To address this problem, we formulate a novel tasks-constrained deep model, which not only learns the inter-task correlation but also employs dynamic task coefficients to facilitate the optimization convergence when learning multiple complex tasks. Extensive evaluations show that the proposed task-constrained learning (i) outperforms existing face alignment methods, especially in dealing with faces with severe occlusion and pose variation, and (ii) reduces model complexity drastically compared to the state-of-the-art methods based on cascaded deep model.
All Author(s) ListZhang ZP, Luo P, Loy CC, Tang XO
Journal nameIEEE Transactions on Pattern Analysis and Machine Intelligence
Detailed descriptiondoi>10.1109/TPAMI.2015.2469286.
Volume Number38
Issue Number5
Pages918 - 930
LanguagesEnglish-United Kingdom
Keywordsconvolutional network; deep learning; Face Alignment; face landmark detection
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; Engineering; Engineering, Electrical & Electronic

Last updated on 2020-02-07 at 04:07