Mayank Mishra

I am currently working as a research assistant at the Indian Institute of Science, Bangalore, under the guidance of Prof. Venkatesh Babu. My interests lie in the application of deep learning for computer vision.

Previously, I finished my undergraduate in computer science at the University of Petroleum and Energy Studies, Dehradun. I have also had the privilege to work under the direction of Dr. Tanupriya Choudhury and Dr. Tanmay Sarkar on various research projects focusing on the applications of computer vision.

Additionally, I have worked as an Associate Data Engineer at Celebal Technologies, where I analyzed large-scale data for a UK-based pharmaceutical company using various machine learning algorithms.

Email | Github | Medium | Resume

Publication(s)

A Closer Look at Smoothness in Domain Adversarial Training
Harsh Rangwani, Sumukh K Aithal, Mayank Mishra , Arihant Jain , & R. Venkatesh Babu

International Conference on Machine Learning (ICML'2022)

Analysed the effect of smoothness of loss landscape in domain adversarial training and achieved SOTA results for domain adaptation on Office-Home and VisDA-2017 datasets.

Paper Code

Allergen30: Detecting food items with possible allergens using deep learning based computer vision
Mayank Mishra, Tanmay Sarkar, Tanupriya Choudhury, Nikunj Bansal, Slim Smaoui, Maksim Rebezov, Mohammad Ali Shariati&, Jose Manuel Lorenzo

Journal: Food Analytical Methods (SCI, IF 3.5, Springer)

Introducing Allergen30, a custom-made dataset with 6,000+ images of 30 commonly used food items that can trigger an allergic reaction within the human body. This work is one of the first research attempts to train a deep learning based object detection model to detect the presence of such food items from images.

Paper Dataset Project description

Devanagari Handwritten Character Recognition
Mayank Mishra, Tanupriya Choudhury, & Tanmay Sarkar,

IEEE India Council International Sub-Sections Conference (INDISCON 21)

Built a devanagari (Indic) script handwritten character classifier using ResNet. The model achieved a SOTA accuracy of 99.72% on the Devanagari Handwritten Character Dataset.

Paper Code Project Description

Patent(s)

CNN based efficient image classification system for smartphone device
Mayank Mishra, Tanupriya Choudhury, & Tanmay Sarkar,

The Patent Office Journal No. 17/2021 Dated 23/04/2021, Pg No. 20373

Articles

	Computer Vision: Image formation and representation Article chosen for further distribution by Medium This article discusses the introductory topics of Computer Vision, namely image formation and representation. The image formation section briefly covers how an image is formed and the factors on which it depends. It also covers the pipeline of image sensing in a digital camera. The second half of the article discusses various ways of image representation and focuses on certain operations that can be performed on images.
	Wondering why do you subtract Gradient in a Gradient Descent Algorithm? The article gives an easy to understand vector calculus insight that feature partial derivatives, gradient and directional derivatives to explain the reason of subtracting gradient in a gradient descent algorithm.
Visit here for more articles

Template modified from here.