Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7728-7737
Abstract
In the field of face recognition, large-scale web-collected datasets are essential for learning discriminative representations, but they suffer from noisy identity labels, such as outliers and label flips. It is beneficial to automatically cleanse their label noise for improving recognition accuracy. Unfortunately, existing cleansing methods cannot accurately identify noise in the wild. To solve this problem, we propose an effective automatic label noise cleansing framework for face recognition datasets, FaceGraph. Using two cascaded graph convolutional networks, FaceGraph performs global-to-local discrimination to select useful data in a noisy environment. Extensive experiments show that cleansing widely used datasets, such as CASIA-WebFace, VGGFace2, MegaFace2, and MS-Celeb-1M, using the proposed method can improve the recognition performance of state-of-the-art representation learning methods like Arcface. Further, we cleanse massive self-collected celebrity data, namely MillionCelebs, to provide 18.8M images of 636K identities. Training with the new data, Arcface surpasses state-of-the-art performance by a notable margin to reach 95.62% TPR at 1e-5 FPR on the IJB-C benchmark.Keywords
This publication has 32 references indexed in Scilit:
- Fine-grained face verification: FGLFW database, baselines, and human-DCMN partnershipPattern Recognition, 2017
- The MegaFace Benchmark: 1 Million Faces for Recognition at Scale2016
- A data-driven approach to cleaning large face datasets2014
- Classification in the Presence of Label Noise: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2013
- All About VLAD2013
- Profiling instances in noise reductionKnowledge-Based Systems, 2012
- Aggregating Local Image Descriptors into Compact CodesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- A comparison of extrinsic clustering evaluation metrics based on formal constraintsInformation Retrieval Journal, 2008
- Improving Classification by Removing or Relabeling Mislabeled Instances2002
- Noise modelling and evaluating learning from examplesArtificial Intelligence, 1996