Deep Learning

Image segmentation using superpixels
Built a segmentation network using SLIC superpixels as input. A pretrained VGG16 network is used with its last few layers replaced by fully connected layers to classify superpixels into classes. (Accuracy 98%)
Image segmentation using superpixels
Optimized a GestureGAN for resource constrained settings
Used MobileNet to optimize cross-view image generation with a 5.7X reduction in parameters.
Optimized a GestureGAN for resource constrained settings