HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Frankenstein: Learning Deep Face Representations using Small Data

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.
Document type :
Journal articles
Complete list of metadata

Cited literature [66 references]  Display  Hide  Download

Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Monday, September 25, 2017 - 9:41:55 AM
Last modification on : Friday, February 4, 2022 - 3:09:20 AM


Files produced by the author(s)




Guosheng Hu, Xiaojiang Peng, Yongxin Yang, Timothy Hospedales, Jakob Verbeek. Frankenstein: Learning Deep Face Representations using Small Data. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2018, 27 (1), pp.293-303. ⟨10.1109/TIP.2017.2756450⟩. ⟨hal-01306168v2⟩



Record views


Files downloads