Surpassing Human-Level Face Verification Performance on LFW with GaussianFace

TL;DR

This paper introduces GaussianFace, a multi-task learning model based on Gaussian Processes that leverages diverse data sources to surpass human-level accuracy in face verification on the LFW benchmark.

Contribution

The paper presents a novel multi-task learning approach using Gaussian Processes to improve face verification across diverse data sources, achieving state-of-the-art results.

Findings

Achieved 98.52% accuracy on LFW benchmark.

Surpassed human-level performance of 97.53% on LFW.

Demonstrated effective generalization to unseen domains.

Abstract

Face verification remains a challenging problem in very complex conditions with large variations such as pose, illumination, expression, and occlusions. This problem is exacerbated when we rely unrealistically on a single training data source, which is often insufficient to cover the intrinsically complex face variations. This paper proposes a principled multi-task learning approach based on Discriminative Gaussian Process Latent Variable Model, named GaussianFace, to enrich the diversity of training data. In comparison to existing methods, our model exploits additional data from multiple source-domains to improve the generalization performance of face verification in an unknown target-domain. Importantly, our model can adapt automatically to complex data distributions, and therefore can well capture complex face variations inherent in multiple sources. Extensive experiments demonstrate the effectiveness of the proposed model in learning from diverse data sources and generalize to unseen domain. Specifically, the accuracy of our algorithm achieves an impressive accuracy rate of 98.52% on the well-known and challenging Labeled Faces in the Wild (LFW) benchmark. For the first time, the human-level performance in face verification (97.53%) on LFW is surpassed.