Deepak Mittal
Indian Institute of Technology Madras
15 Papers
55 Citations
Deepak Mittal is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 5, co-authored 12 publications.
Chat about Author
Papers
Studying the plasticity in deep convolutional neural networks using random pruning
Deepak Mittal,Shweta Bhardwaj,Mitesh M. Khapra,Balaraman Ravindran +3 more
- 01 Mar 2019
TL;DR: Recently, there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations as discussed by the authors, where the low-scoring filters are pruned away, the remainder of the network is fine-tuned and is shown to give performance comparable to the original unpruned network.
31
•Posted Content
Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning
TL;DR: This work reports experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen, but to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.
25
Training a deep learning architecture for vehicle detection using limited heterogeneous traffic data
Deepak Mittal,Avinash Reddy,Gitakrishnan Ramadurai,Kaushik Mitra,Balaraman Ravindran +4 more
- 01 Jan 2018
TL;DR: This work combines an existing large general (non-traffic) dataset with a small low-resolution heterogeneous traffic dataset and obtains state-of-the-art vehicle detection performance.
25
Investigating feature selection and explainability for COVID-19 diagnostics from cough sounds
Avila Flavio,Amir Hossein Poorjam,Deepak Mittal,Charles Dognin,Ananya Muguli,Rohit Kumar,Srikanth Raj Chetupalli,Sriram Ganapathy,Maneesh Singh +8 more
- 30 Aug 2021
TL;DR: The proposed system, which ranked 9th on the 2021 Diagnosing COVID-19 using Acoustics (Di- COVA) challenge leaderboard, obtained an area under the receiver operating characteristic curve (AUC) of 0:81 on the blind test data set, which is a 10:9% absolute improvement compared to the baseline.
13
The Effect of Pretraining on Extractive Summarization for Scientific Documents
Yash Kumar Gupta,Pawan Sasanka Ammanamanchi,Shikha Bordia,Arjun Manoharan,Deepak Mittal,Ramakanth Pasunuru,Manish Shrivastava,Maneesh Singh,Mohit Bansal,Preethi Jyothi +9 more
- 01 Jun 2021
TL;DR: This work derives significant performance improvements using an intermediate pretraining step that leverages existing summarization datasets and reports state-of-the-art results on a recently released scientific summarization dataset, SciTLDR.