Boosting Unconstrained Face Recognition with Auxiliary Unlabeled Data
This addresses the challenge of improving face recognition in unconstrained settings for applications like security and surveillance, offering a practical solution by leveraging easily acquired unlabeled data, though it is incremental as it builds on existing methods.
The paper tackles the problem of poor generalization in face recognition models trained on limited labeled datasets by using auxiliary unlabeled data to learn more generalizable face representations, achieving appreciable performance gains and outperforming supervised baselines with less labeled data on benchmarks like IJB-B, IJB-C, and IJB-S.
In recent years, significant progress has been made in face recognition, which can be partially attributed to the availability of large-scale labeled face datasets. However, since the faces in these datasets usually contain limited degree and types of variation, the resulting trained models generalize poorly to more realistic unconstrained face datasets. While collecting labeled faces with larger variations could be helpful, it is practically infeasible due to privacy and labor cost. In comparison, it is easier to acquire a large number of unlabeled faces from different domains, which could be used to regularize the learning of face representations. We present an approach to use such unlabeled faces to learn generalizable face representations, where we assume neither the access to identity labels nor domain labels for unlabeled images. Experimental results on unconstrained datasets show that a small amount of unlabeled data with sufficient diversity can (i) lead to an appreciable gain in recognition performance and (ii) outperform the supervised baseline when combined with less than half of the labeled data. Compared with the state-of-the-art face recognition methods, our method further improves their performance on challenging benchmarks, such as IJB-B, IJB-C and IJB-S.