Large-scale Bisample Learning on ID Versus Spot Face Recognition
arXiv:1806.03018
Abstract
In real-world face recognition applications, there is a tremendous amount of data with two images for each person. One is an ID photo for face enrollment, and the other is a probe photo captured on spot. Most existing methods are designed for training data with limited breadth (a relatively small number of classes) and sufficient depth (many samples for each class). They would meet great challenges on ID versus Spot (IvS) data, including the under-represented intra-class variations and an excessive demand on computing devices. In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition. To tackle the bisample problem with only two samples for each class, a classification-verification-classification (CVC) training strategy is proposed to progressively enhance the IvS performance. Besides, a dominant prototype softmax (DP-softmax) is incorporated to make the deep learning scalable on large-scale classes. We conduct LBL on a IvS face dataset with more than two million identities. Experimental results show the proposed method achieves superior performance to previous ones, validating the effectiveness of LBL on IvS face recognition.
arXiv commentAccepted by special issue on Deep Learning for Face Analysis. International Journal of Computer Vision (IJCV), 2019
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Learning Face Representation by Joint Identification-Verification
- Learning Face Representation from Scratch
- Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?
- A Light CNN for Deep Face Representation with Noisy Labels
- One-shot Face Recognition by Promoting Underrepresented Classes
- Smart Mining for Deep Metric Learning
- FaceBoxes: A CPU Real-time Face Detector with High Accuracy
- How to Train Triplet Networks with 100K Identities?
- Web-Scale Training for Face Identification
- Few-Shot Object Recognition from Machine-Labeled Web Images