One-shot Face Recognition by Promoting Underrepresented Classes

Abstract

In this paper, we study the problem of training large-scale face identification model with imbalanced training data. This problem naturally exists in many real scenarios including large-scale celebrity recognition, movie actor annotation, etc. Our solution contains two components. First, we build a face feature extraction model, and improve its performance, especially for the persons with very limited training samples, by introducing a regularizer to the cross entropy loss for the multi-nomial logistic regression (MLR) learning. This regularizer encourages the directions of the face features from the same class to be close to the direction of their corresponding classification weight vector in the logistic regression. Second, we build a multi-class classifier using MLR on top of the learned face feature extraction model. Since the standard MLR has poor generalization capability for the one-shot classes even if these classes have been oversampled, we propose a novel supervision signal called underrepresented-classes promotion loss, which aligns the norms of the weight vectors of the one-shot classes (a.k.a. underrepresented-classes) to those of the normal classes. In addition to the original cross entropy loss, this new loss term effectively promotes the underrepresented classes in the learned model and leads to a remarkable improvement in face recognition performance. We test our solution on the MS-Celeb-1M low-shot learning benchmark task. Our solution recognizes 94.89% of the test images at the precision of 99\% for the one-shot classes. To the best of our knowledge, this is the best performance among all the published methods using this benchmark task with the same setup, including all the participants in the recent MS-Celeb-1M challenge at ICCV 2017.

References in corpus (5)

• Learning Face Representation from Scratch
• DeepID3: Face Recognition with Very Deep Neural Networks
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
• Range Loss for Deep Face Recognition with Long-tail

Cited by in corpus (24)

• Deep Face Recognition: A Survey
• Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
• Incremental Classifier Learning with Generative Adversarial Networks
• Efficient Facial Representations for Age, Gender and Identity Recognition in Organizing Photo Albums using Multi-output CNN
• BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
• Deep Learning Based Single Sample Per Person Face Recognition: A Survey
• Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning
• Maintaining Discrimination and Fairness in Class Incremental Learning
• Deep Imbalanced Learning for Face Recognition and Attribute Prediction
• Feature Transfer Learning for Deep Face Recognition with Under-Represented Data
• To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions
• Large-scale Bisample Learning on ID Versus Spot Face Recognition
• Generative One-Shot Face Recognition
• Faster Optimization-Based Meta-Learning Adaptation Phase
• Large Scale Incremental Learning
• Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
• Angular Learning: Toward Discriminative Embedded Features
• Semi-Siamese Training for Shallow Face Learning
• Improving precision and recall of face recognition in SIPP with combination of modified mean search and LSH
• Towards Fair Cross-Domain Adaptation via Generative Learning
• Unsupervised Part Segmentation through Disentangling Appearance and Shape
• Affect-DML: Context-Aware One-Shot Recognition of Human Affect using Deep Metric Learning
• Procrustean Training for Imbalanced Deep Learning
• Scalable Object Detection for Stylized Objects