Frankenstein: Learning Deep Face Representations using Small Data
arXiv:1603.06470
Abstract
Deep convolutional neural networks have recently proven extremely effective for difficult face recognition problems in uncontrolled settings. To train such networks, very large training sets are needed with millions of labeled images. For some applications, such as near-infrared (NIR) face recognition, such large training datasets are not publicly available and difficult to collect. In this work, we propose a method to generate very large training datasets of synthetic images by compositing real face images in a given dataset. We show that this method enables to learn models from as few as 10,000 training images, which perform on par with models trained from 500,000 images. Using our approach we also obtain state-of-the-art results on the CASIA NIR-VIS2.0 heterogeneous face recognition dataset.
IEEE TIP
References in corpus (11)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Learning Face Representation from Scratch
- DeepID3: Face Recognition with Very Deep Neural Networks
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Face Alignment in Full Pose Range: A 3D Total Solution
- MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
- On Rendering Synthetic Images for Training an Object Detector
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- Deeply learned face representations are sparse, selective, and robust
- When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
- Effective Face Frontalization in Unconstrained Images