no code implementations • 4 Sep 2017 • Manik Goyal, Param Rajpura, Hristo Bojinov, Ravi Hegde
Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock for further improvements.
no code implementations • 21 Jun 2017 • Param S. Rajpura, Hristo Bojinov, Ravi S. Hegde
A further increase of 12% in the mAP is obtained by adding only 400 real images to these 4000 synthetic images in the training set.
no code implementations • 21 Jun 2017 • Ramkumar B, R. S. Hegde, Rob Laber, Hristo Bojinov
The CUDA based parallel implementation is described in detail with fine-grained comparison between the GPU and CPU implementations.
no code implementations • 6 Aug 2014 • Hristo Bojinov, Yan Michalevsky, Gabi Nakibly, Dan Boneh
We demonstrate how the multitude of sensors on a smartphone can be used to construct a reliable hardware fingerprint of the phone.
Cryptography and Security