277 citations · 473 across the 13 of their papers we have counts for
Showing 2017 · cs.CVShow all
2 papers · 2 filters
cs.CV2017
The Do's and Don'ts for CNN-based Face Verification
Ankan Bansal, Carlos Castillo, Rajeev Ranjan +1
While the research community appears to have developed a consensus on the methods of acquiring annotated data, design and training of CNNs, many questions still remain to be answer…
cs.CV2017★ 277 cited
L2-constrained Softmax Loss for Discriminative Face Verification
Rajeev Ranjan, Carlos D. Castillo, Rama Chellappa
In recent years, the performance of face verification systems has significantly improved using deep convolutional neural networks (DCNNs). A typical pipeline for face verification…