FAME: Face Association through Model Evolution

TL;DR

FAME is a novel iterative method that refines face models from noisy web data by pruning outliers, leading to improved face identification performance on benchmark datasets.

Contribution

The paper introduces FAME, a new approach for learning face models from weakly-labelled, noisy web data through iterative model evolution and data pruning.

Findings

Comparable or better than state-of-the-art on benchmarks

Effective in handling noisy, weakly-labelled data

Improves face identification accuracy

Abstract

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.