Facing scalability: Naming faces in an online social network

Automatically naming faces in online social networks enables us to search for photos and build user face models. We consider two common weakly supervised settings where: (1) users are linked to photos, not to faces and (2) photos are not labeled but part of a user's album. The focus is on algorithms that scale up to an entire online social network. We extensively evaluate different graph-based strategies to label faces in both settings and consider dependencies. We achieve results on a par with a recent multi-person approach, but with 60 times less computation time on a set of 300K weakly labeled faces and 1.4 M faces in user albums. A subset of the faces can be labeled with a speed-up of over three orders of magnitude.

► We introduce face naming strategies for two types of weakly labeled faces.
► We focus on strategies that scale well to large numbers of users and faces.
► We introduce a face dataset with 1.7 M faces obtained from an online social network.
► We thoroughly investigate the factors that influence the face naming results.
► We achieve state-of-the-art performance with a significantly lower computation time.