Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
This work addresses the problem of improving accuracy in unconstrained face verification and recognition systems, which is incremental as it builds on existing deep learning pipelines with a novel loss function.
The paper tackled the performance gap in face verification and recognition by proposing Crystal Loss, a new loss function that restricts features to a hypersphere, achieving state-of-the-art results on datasets like LFW, IJB-A, IJB-B, and IJB-C across false alarm rates from 10^-1 to 10^-7.
In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for face verification includes training a deep network for subject classification with softmax loss, using the penultimate layer output as the feature descriptor, and generating a cosine similarity score given a pair of face images or videos. The softmax loss function does not optimize the features to have higher similarity score for positive pairs and lower similarity score for negative pairs, which leads to a performance gap. In this paper, we propose a new loss function, called Crystal Loss, that restricts the features to lie on a hypersphere of a fixed radius. The loss can be easily implemented using existing deep learning frameworks. We show that integrating this simple step in the training pipeline significantly improves the performance of face verification and recognition systems. We achieve state-of-the-art performance for face verification and recognition on challenging LFW, IJB-A, IJB-B and IJB-C datasets over a large range of false alarm rates (10-1 to 10-7).