activity
20172020
most citedOnline Ensemble Model Compression using Knowledge Distillation

45 citations · 48 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV202045 cited

Online Ensemble Model Compression using Knowledge Distillation

Devesh Walawalkar, Zhiqiang Shen, Marios Savvides

This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble kno…

cs.LG2019

O-MedAL: Online Active Deep Learning for Medical Image Analysis

Asim Smailagic, Pedro Costa, Alex Gaudio +9

Active Learning methods create an optimized labeled training set from unlabeled data. We introduce a novel Online Active Deep Learning method for Medical Image Analysis. We extend…

cs.CV2018

An Empirical Analysis of Deep Audio-Visual Models for Speech Recognition

Devesh Walawalkar, Yihui He, Rohit Pillai

In this project, we worked on speech recognition, specifically predicting individual words based on both the video frames and audio. Empowered by convolutional neural networks, the…

cs.CV2018

MedAL: Deep Active Learning Sampling Method for Medical Image Analysis

Asim Smailagic, Hae Young Noh, Pedro Costa +6

Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance.Deep learning model…

cs.CV20181 cited

A fully automated framework for lung tumour detection, segmentation and analysis

Devesh Walawalkar

Early and correct diagnosis is a very important aspect of cancer treatment. Detection of tumour in Computed Tomography scan is a tedious and tricky task which requires expert knowl…

cs.CV20172 cited

Grammatical facial expression recognition using customized deep neural network architecture

Devesh Walawalkar

This paper proposes to expand the visual understanding capacity of computers by helping it recognize human sign language more efficiently. This is carried out through recognition o…