Triplet probabilistic embedding for face verification and clustering
Swami Sankaranarayanan, Azadeh Alavi, Carlos D. Castillo, Rama Chellappa · 2016
Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding step, learned using triplet probability constraints to address the unconstrained face verification problem. Aside from yielding performance improvements, this embedding provides significant advantages in terms of memory and for post-processing operations like subject specific clustering. Experiments on the challenging IJB-A dataset show that the proposed algorithm performs close to the state of the art methods in verification and identification metrics, while requiring much less training data and training/test time. The superior performance of the proposed method on the CFP dataset shows that the representation learned by our deep CNN is robust to large pose variation. Furthermore, we demonstrate the robustness of deep features to challenges including age, pose, blur and clutter by performing simple clustering experiments on both IJB-A and LFW datasets.