Towards Flops-constrained Face Recognition

09/02/2019
by   Yu Liu, et al.
1

Large scale face recognition is challenging especially when the computational budget is limited. Given a 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 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 function `ArcNegFace', 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 the `PolyFace+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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/29/2019

AirFace:Lightweight and Efficient Model for Face Recognition

With the development of convolutional neural network, significant progre...
research
10/04/2021

Balanced Masked and Standard Face Recognition

We present the improved network architecture, data augmentation, and tra...
research
08/18/2021

Masked Face Recognition Challenge: The InsightFace Track Report

During the COVID-19 coronavirus epidemic, almost everyone wears a facial...
research
05/18/2021

Analyzing the effectiveness of image augmentations for face recognition from limited data

This work presents an analysis of the efficiency of image augmentations ...
research
08/16/2021

Masked Face Recognition Challenge: The WebFace260M Track Report

According to WHO statistics, there are more than 204,617,027 confirmed C...
research
04/18/2018

SFace: An Efficient Network for Face Detection in Large Scale Variations

Face detection serves as a fundamental research topic for many applicati...
research
08/29/2022

Towards Robust Face Recognition with Comprehensive Search

Data cleaning, architecture, and loss function design are important fact...

Please sign up or login with your details

Forgot password? Click here to reset