Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face Recognition
- 16 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 16 (15566013) , 3082-3095
Abstract
Face recognition systems are sometimes deployed to a target domain with limited unlabeled samples available. For instance, a model trained on the large-scale webfaces may be required to adapt to a NIR-VIS scenario via very limited unlabeled faces. This situation poses a great challenge to Unsupervised Domain Adaptation with Limited samples for Face Recognition (UDAL-FR), which is less studied in previous works. In this paper, with deep learning methods, we propose a novel training remedy by decomposing the model into the weight parameters and the BN statistics in the training phase. Based on decomposing, we design a novel framework via meta-learning, called Decomposed Meta Batch Normalization (DMBN) for fast domain adaptation in face recognition. DMBN trains the network such that domain-invariant information is prone to store in the weight parameters and domain-specific knowledge tends to be represented by the BN statistics. Specifically, DMBN constructs distribution-shifted tasks via domain-aware sampling, on which several meta-gradients are obtained by optimizing discriminative representations across different BNs. Finally, the weight parameters are updated with these meta-gradients for better consistency across different BNs. With the learned weight parameters, the adaptation is very fast since only the BN updating on limited data is needed. We propose two UDAL-FR benchmarks to evaluate the domain-adaptive ability of a model with limited unlabeled samples. Extensive experiments validate the efficacy of our proposed DMBN.Keywords
Funding Information
- National key research and development program (2020YFC2003901)
- Chinese National Natural Science Foundation (61876178, 61806196, 61976229, 61872367)
This publication has 42 references indexed in Scilit:
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition2016
- Cross-Modality Feature Learning Through Generic Hierarchical Hyperlingual-WordsIEEE Transactions on Neural Networks and Learning Systems, 2016
- Simultaneous Deep Transfer Across Domains and Tasks2015
- FaceNet: A unified embedding for face recognition and clustering2015
- Deep Learning Face Representation from Predicting 10,000 Classes2014
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- Learning Discriminant Face DescriptorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- The CASIA NIR-VIS 2.0 Face Database2013
- Face recognition in unconstrained videos with matched background similarity2011
- Updating Formulae and a Pairwise Algorithm for Computing Sample Variances1982