Unconstrained Face Verification using Deep CNN Features
This work addresses face verification in real-world, unconstrained environments, which is an incremental improvement over existing methods on harder datasets.
The paper tackles unconstrained face verification by using deep convolutional neural network features, achieving evaluation on the challenging IARPA Janus Benchmark A dataset with 500 subjects and variations in pose and illumination.
In this paper, we present an algorithm for unconstrained face verification based on deep convolutional features and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset. The IJB-A dataset includes real-world unconstrained faces from 500 subjects with full pose and illumination variations which are much harder than the traditional Labeled Face in the Wild (LFW) and Youtube Face (YTF) datasets. The deep convolutional neural network (DCNN) is trained using the CASIA-WebFace dataset. Extensive experiments on the IJB-A dataset are provided.