Face attribute recognition plays a vital role in face-related tasks. Common face attributes include person age, person gender, mask-wearing, glasses-wearing, etc. Using one network to predict all attributes can save many computation costs. However, these attributes can hardly be fully labelled on every image in the same dataset since the labelling costs and the requirement on the sample balance. In many cases, each of the datasets are labelled with a single attribute. With several such datasets, how to use one network to generate the multi-task predictions for all attributes is a problem. In this paper, we propose a two-level iteration training method for multi-task face attribute learning with task-isolated labels. The two-level iteration method includes a task-level inner iteration and the regular outer iteration. With this scheme, the network receives the gradients from all tasks after each inner iteration. After training, the network is able to predict all attributes. Experiments show the effectiveness of the method and the advantages of multi-task learning over single-task learning on network accuracy and efficiency, which demonstrate the broad applicability and effectiveness of the proposed approach.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.