An End-to-End System for Unconstrained Face Verifcation with Deep Convolutional Neural Networks

Jun-Cheng Chen, Rajeev Ranjan, Swami Sankaranarayanan, Amit Kumar, Ching-Hui Chen, Vishal M. Patel, Carlos D. Castillo, Rama Chellappa
A.V. Williams 4455, University of Maryland, College Park, MD 20740, USA
arXiv:1605.02686 [cs.CV], (9 May 2016)


   title={An End-to-End System for Unconstrained Face Verifcation with Deep Convolutional Neural Networks},

   author={Chen, Jun-Cheng and Ranjan, Rajeev and Sankaranarayanan, Swami and Kumar, Amit and Chen, Ching-Hui and Patel, Vishal M. and Castillo, Carlos D. and Chellappa, Rama},






Download Download (PDF)   View View   Source Source   



Over the last four years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems. This has been made possible due to the availability of large annotated datasets, a better understanding of the non-linear mapping between input images and class labels as well as the affordability of GPUs. In this paper, we present the design details of a deep learning system for end-to-end unconstrained face verification/recognition. The quantitative performance evaluation is conducted using the newly released IARPA Janus Benchmark A (IJB-A), the JANUS Challenge Set 2 (JANUS CS2), and the LFW dataset. The IJB-A dataset includes real-world unconstrained faces of 500 subjects with significant pose and illumination variations which are much harder than the Labeled Faces in ihe Wild (LFW) and Youtube Face (YTF) datasets. JANUS CS2 is the extended version of IJB-A which contains not only all the images/frames of IJB-A but also includes the original videos for evaluating video-based face verification system. Some open issues regarding DCNNs for object recognition problems are then discussed.
Rating: 2.5. From 1 vote.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: