Aiming to reduce the computational cost of Softmax in massive label space of Face Recognition (FR) benchmarks, recent studies estimate the output using a subset of identities. Although promising, the association between the computation cost and the number of identities in the dataset remains linear only with a reduced ratio. A shared characteristic among available FR methods is the employment of atomic scalar labels during training. Consequently, the input to label matching is through a dot product between the feature vector of the input and the Softmax centroids. Inspired by generative modeling, we present a simple yet effective method that substitutes scalar labels with structured identity code, i.e., a sequence of integers. Specifically, we propose a tokenization scheme that transforms atomic scalar labels into structured identity codes. Then, we train an FR backbone to predict the code for each input instead of its scalar label. As a result, the associated computational cost becomes logarithmic w.r.t. number of identities. We demonstrate the benefits of the proposed method by conducting experiments. In particular, our method outperforms its competitors by 1.52%, and 0.6% at TAR@FAR on IJB-B and IJB-C, respectively, while transforming the association between computational cost and the number of identities from linear to logarithmic. See code atthis https URL
View on arXiv@article{ebrahimi2025_2505.03012,
title={ GIF: Generative Inspiration for Face Recognition at Scale },
author={ Saeed Ebrahimi and Sahar Rahimi and Ali Dabouei and Srinjoy Das and Jeremy M. Dawson and Nasser M. Nasrabadi },
journal={arXiv preprint arXiv:2505.03012},
year={ 2025 }
}