Computer Vision

Online Ensemble Model Compression using Knowledge Distillation

This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each model learns …

Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification

Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional dropout …

Human Driver Drowsiness Detection

Artifical Intelligence based iOS application for detecting driver drowsiness

Forecasting Path from Expert Demonstrations

Research on path forecasting for self driving vehicle using CARLA simulator

Deep Audio-Visual Model for Speech Recognition

Research on infusing attention mechanism for combined Deep Audio-Visual Models