Feature Transfer Learning for Face Recognition With Under-Represented Data

By Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu, Manmohan Chandraker. 2019

326 citations recorded by the source corpus.

Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data. Training with under-represented data leads to biased classifiers in conventionally-trained deep networks. In this paper, we propose a center-based feature transfer framework to augment the feature space of under-represented subjects from the regular subjects that have sufficiently diverse samples. A Gaussian prior of the variance is assumed across all subjects and the variance from regular ones are transferred to the under-represented ones. This encourages the under-represented distribution to be closer to the regular distribution. Further, an alternating training regimen is proposed to simultaneously achieve less biased classifiers and a more discriminative feature representation. We conduct ablative study to mimic the under-represented datasets by varying the portion of under-represented classes on the MS-Celeb-1M dataset. Advantageous results on LFW, IJB-A and MS-Celeb-1M demonstrate the effectiveness of our feature transfer and training strategy, compared to both general baselines and state-of-the-art methods. Moreover, our feature transfer successfully presents smooth visual interpolation, which conducts disentanglement to preserve identity of a class while augmenting its feature space with non-identity variations such as pose and lighting.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Long-Tailed Class Incremental Learning (2022, background): “Recently, transfer learning [24,44] between head and tail classes, two-stage learning [16,50] to decouple representation and classifier learning, and ensemble learning [42,39] of different experts have achieved superior performance.”
Imbalanced Continual Learning with Partitioning Reservoir Sampling (2020, background): “Mainly due to the lack of data, the minority classes are much under-represented within the learned features relative to the majority [92,21].”
Decoupling Representation and Classifier for Long-Tailed Recognition (2019, background): “variance (Yin et al., 2019) and transferring semantic deep features (Liu et al.”
Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection (2021, background): “Other approaches like transfer learning [45], metric learning [46] could also be used to resolve the class imbalance problem.”
Deep Face Recognition: A Survey (2018, background): “[251] augmented feature space of low-shot classes by transferring the principal components from regular to low-shot classes to encourage the variance of low-shot classes to mimic that of regular classes.”
ELF: An Early-Exiting Framework for Long-Tailed Classification (2020, background): “Transfer and meta learning based approaches aims to transfer knowledge from the majority classes to rare ones by transfer learning, multi task learning or learning to learn [12, 27, 28].”
Delving into Deep Imbalanced Regression (2021, unknown): “…(Cao et al., 2019; Cui et al., 2019; Dong et al., 2019; Huang et al., 2016; 2019), and leveraging relevant learning paradigms, including transfer learning (Yin et al., 2019), metric learning (Zhang et al., 2017), meta-learning (Shu et al., 2019), and two-stage training (Kang et al., 2020).”
Past, Present, and Future of Face Recognition: A Review (2020, background): “Several promising ideas have been explored to bring advances in CNNs, such as the use of proper activation [143] and various loss functions [15,124–126,130,134,136,138,141,142,145,148–152], the use of metric learning algorithms [38,127], normalization of features and weights [133,135,139], extractio”
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective (2020, background): “transfer intra-class variance from the head to tail [56], Liu et al.”
Rethinking the Value of Labels for Improving Class-Imbalanced Learning (2020, background): “Other learning paradigms, including transfer learning [33, 54], metric learning [55, 58], and meta-learning [1, 45], have also been explored.”
Equalization Loss for Long-Tailed Object Recognition (2020, background): “[43] augments the feature space of tail classes by transferring the feature variance of regular classes that have sufficient training samples.”
Cross-Domain Similarity Learning for Face Recognition in Unseen Domains (2021, background): “Efforts in addressing unseen scenarios are either on transferring existing class variances to under-represented classes [47], or learning universal features through various augmentations [37].”
Balanced Knowledge Distillation for Long-tailed Learning (2021, background): “, distributions [53, 31], memory features [33] or meta-knowledge [50], from head to tail classes.”