Towards Flops-constrained Face Recognition

Abstract: Large scale face recognition is challenging especially when the computational budget is limited. Given a \textit{flops} upper bound, the key is to find the optimal neural network architecture and optimization method. In this article, we briefly introduce the solutions of team 'trojans' for the ICCV19 - Lightweight Face Recognition Challenge~\cite{lfr}. The challenge requires each submission to be one single model with the computational budget no higher than 30 GFlops. We introduce a searched network architecture Efficient PolyFace' based on the Flops constraint, a novel loss functionArcNegFace', a novel frame aggregation method QAN++', together with a bag of useful tricks in our implementation (augmentations, regular face, label smoothing, anchor finetuning, etc.). Our basic model,Efficient PolyFace', takes 28.25 Gflops for the deepglint-large' image-based track, and thePolyFace+QAN++' solution takes 24.12 Gflops for the `iQiyi-large' video-based track. These two solutions achieve 94.198\% @ 1e-8 and 72.981\% @ 1e-4 in the two tracks respectively, which are the state-of-the-art results.