About Me

I am currently working as Master Data Scientist II at AI Center of Excellence, Deloitte. I am working in the intersection of Computer Vision and Deep Learning. I am also exploring Self Supervised Learning methods in Speech Processing.
I am also a first year PhD (External) scholar at the Department of Artificial Intelligence, Indian Institute of Technology, Hyderabad under the supervision of Dr. Vineeth N Balasubramanian. Prior to that I completed my M.S. (Research) under the supervision of Dr. Balaraman Ravindran and co-guided by Dr. Gitakrishnan Ramadurai from the Department of Computer Science and Technology , Indian Institute of Technology Madras . My thesis was focused on Model compression and Filter Pruning in Deep Convolutional Networks. I also worked on Vehicle Detection in Heterogeneous traffic scenarios. My M.S. research was sponsored by Intel India Research.

[Google Scholar] [LinkedIn]

Publications

• Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection. Debottam Dutta, Debarpan Bhattacharya, Sriram Ganapathy, Amir Poorjam, Deepak Mittal, Maneesh Singh. Proceedings of Interspeech (23rd Annual Conference of ISCA), 2022. [Paper]


• SPLICEOUT: A Simple and Efficient Audio Augmentation Method. Arjit Jain, Pranay Reddy Samala, Deepak Mittal, Preethi Jyothi, Maneesh Singh. Proceedings of Interspeech (23rd Annual Conference of ISCA), 2022. [Paper]


• DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning. Sreyan Ghosh, Ashish Seth, Deepak Mittal, Maneesh Singh and S. Umesh. Accepted at The 2nd Workshop on Self-supervised Learning for Audio and Speech Processing, AAAI 2022. [Paper]


• Investigating Feature Selection and Explainability for COVID-19 Diagnostics from Cough Sounds . Flavio Avila, Amir H. Poorjam, Deepak Mittal, Charles Dognin, Ananya Muguli, Rohit Kumar,Srikanth Raj Chetupalli, Sriram Ganapathy and Maneesh Singh. Proceedings of Interspeech (22nd Annual Conference of ISCA), 2021. [Paper]


• The Effect of Pretraining on Extractive Summarization for Scientific Documents . Yash Gupta, Pawan Sasanka Ammanamanchi, Shikha Bordia, Arjun Manoharan, Deepak Mittal, Ramakanth Pasunuru, Manish Shrivastava, Maneesh Singh, Mohit Bansal and Preethi Jyothi. Accepted at 2nd workshop on Scholarly Document Processing at NAACL 2021. [Paper]


• Perturb, Predict & Paraphrase: Semi-supervised Learning using Noisy Student for Image Captioning . Arjit Jain, Pranay Reddy Samala, Preethi Jyothi, Deepak Mittal, Maneesh Singh. Accepted at the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021). [Paper][Video][Code]


• ProAlignNet : Unsupervised Learning for Progressively Aligning Noisy Contours . VSR Veeravasarapu, Abhishek Goel, Deepak Mittal, Maneesh Singh. Accepted at Conference on Computer Vision and Pattern Recognition (CVPR 2020). [Paper] [Video]


• Studying Plasticity in Deep Convolutional Neural Networks using Random Pruning . Deepak Mittal, Shweta Bhardwaj, Mitesh M Khapra, Balaraman Ravindran. (Invited Paper) Journal of Machine Vision And Applications (MVA 2019). [Paper]


• Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks . Deepak Mittal*, Shweta Bhardwaj*, Mitesh M Khapra, Balaraman Ravindran. Accepted at IEEE Winter Conference on Applications of Computer Vision (WACV 2018). [Paper][Code]


• Training a Deep Learning Architecture for Vehicle Detection Using Limited Heterogeneous Traffic Data . Deepak Mittal, Avinash Reddy, Gitakrishnan Ramadurai, Kaushik Mitra, Balaraman Ravindran. Accepted at (COMSNETS 2018) Workshop on Intelligent Transportation Systems. [Paper][Dataset]

Dissertation

You can find my M.S. dissertation here: Exploring the Plasticity of Deep Convolutional Neural Networks

Work Experience

• Worked as Machine Learning Engineer II at Verisk|AI from August 2018 to April 2022.


• Project Associate at RISE-IIL IIT Madras from Jan 2015 to July 2018 (Sponsored by Ministry of Urban Development and Intel Research).


• Intenrship at IBM Research Lab Bangalore from May 2015 to July 2015.


• Worked in Safenet Infotech (now Thales) as an Associate Software Engineer from July 2013 to Jan 2015.


• Internship at Safenet Infotech (now Thales) from Jan 2013 to June 2013.

Contact:

deepak [at] cse [dot] iitm [dot] ac [dot] in.