FAME: Face Association through Model Evolution
This addresses the challenge of noisy data in face recognition for applications like public figure identification, though it is incremental as it builds on existing methods for data pruning.
The paper tackles the problem of learning face models from noisy, weakly-labeled web images by proposing FAME, an iterative method that prunes outliers based on discriminativeness and representativeness, achieving results comparable to or better than state-of-the-art on benchmark datasets for face identification.
We attack the problem of learning face models for public faces from weakly-labelled images collected from web through querying a name. The data is very noisy even after face detection, with several irrelevant faces corresponding to other people. We propose a novel method, Face Association through Model Evolution (FAME), that is able to prune the data in an iterative way, for the face models associated to a name to evolve. The idea is based on capturing discriminativeness and representativeness of each instance and eliminating the outliers. The final models are used to classify faces on novel datasets with possibly different characteristics. On benchmark datasets, our results are comparable to or better than state-of-the-art studies for the task of face identification.