Triplet Similarity Embedding for Face Verification
This improves face verification accuracy and efficiency for security or identification applications, though it appears incremental.
The authors tackled face verification by coupling a deep CNN with a low-dimensional discriminative embedding learned using triplet similarity constraints, achieving state-of-the-art performance on the IJB-A dataset with reduced training time.
In this work, we present an unconstrained face verification algorithm and evaluate it on the recently released IJB-A dataset that aims to push the boundaries of face verification methods. The proposed algorithm couples a deep CNN-based approach with a low-dimensional discriminative embedding learnt using triplet similarity constraints in a large margin fashion. Aside from yielding performance improvement, this embedding provides significant advantages in terms of memory and post-processing operations like hashing and visualization. Experiments on the IJB-A dataset show that the proposed algorithm outperforms state of the art methods in verification and identification metrics, while requiring less training time.