Learning Unified Representations for Multi-Resolution Face Recognition
Hulingxiao He (School of Automation,Beijing Institute of Technology), Wu Yuan (School of Computer Science,Beijing Institute of Technology),* Yidian Huang (Beijing Institute of Technology), Shilong Zhao (Beijing Institute of Technology), Wen Yuan (State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS), Hanqing Li (University of the Chinese Academy of Sciences)
The 34th British Machine Vision Conference
Abstract
In this work, we propose Branch-to-Trunk network (BTNet), a novel representation learning method for multi-resolution face recognition. It consists of a trunk network (TNet), namely a unified encoder, and multiple branch networks (BNets), namely resolution adapters. As per the input, a resolution-specific BNet is used and the output are implanted as feature maps in the feature pyramid of TNet, at a layer with the same resolution. The discriminability of tiny faces is significantly improved, as the interpolation error introduced by rescaling, especially up-sampling, is mitigated on the inputs. With branch distillation and backward-compatible training, BTNet transfers discriminative high-resolution information to multiple branches while guaranteeing representation compatibility. Our experiments demonstrate strong performance on face recognition benchmarks, both for multi-resolution identity matching and feature aggregation, with much less computation amount and parameter storage. We establish new state-of-the-art on the challenging QMUL-SurvFace 1: N face identification task. Our code is available at https://github.com/StevenSmith2000/BTNet.Video
Citation
@inproceedings{He_2023_BMVC,
author = {Hulingxiao He and Wu Yuan and Yidian Huang and Shilong Zhao and Wen Yuan and Hanqing Li},
title = {Learning Unified Representations for Multi-Resolution Face Recognition},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0320.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by