Nowadays, deep learning has been able to challenge or even outperform human understanding in vision related tasks. However, these advancements are driven by the immense computational power requirements and use of very deep and complicated architectures, trained on millions of data. Thus, innovation gets bound by the GPU requirements, amount of annotated data present and the resources present.
My work primarily focuses on maximising the performance of an algorithm under limited resources by proposing novel training techniques or architectures which give comparable results. These improved exploration techniques using deep learning can work with less annotated data, less resource requirements and are more generalised. Being a research enthusiast, I want to explore new learning methods, novel architectures and cost effective methods to reduce our dependencies on high-end resources.
Ph.D in Computer Vision and Pattern Recognition
Department of Computer Science and Engineering
Indian Institute of Technology, Kharagpur
M.S. in Computer Science and Engineering
M.S. Thesis: "Study of Land Cover using Polarimetric Synthetic Aperture Radar (SAR) Image Processing"
Department of Computer Science and Engineering
Indian Institute of Technology, Kharagpur
B.Tech. in Electronics and Communication
Electronics and Communication Department
Institute of Engineering and Management, Kolkata
Senior/Junior Research Fellow
Department of Computer Science and Engineering
In collaboration with Science and Engineering Research Board (SERB)
Indian Institute of Technology, Kharagpur
Research Assistant
Department of Computer Science and Engineering
In collaboration with Indian Space Research Organisation (ISRO).
Indian Institute of Technology, Kharagpur
Javascript Developer
Fusioncharts, Kolkata
Dr. Jayanta Mukhopadhyay
Professor, Department of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal 721302
Dean Outreach and Alumni Affairs, IIT Kharagpur
Website: http://www.facweb.iitkgp.ac.in/~jay/
Dr. Partha Pratim Das
Visiting Professor, Department of Computer Science
Ashoka University, Sonipat, Haryana 131029
(On Leave) Professor, Department of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal 721302
Website: ps://www.ashoka.edu.in/profile/partha-pratim-das/
LinkedIn: https://www.linkedin.com/in/ppdas/
December '23: Pal, Shankho Subhra, Ankita Chatterjee, Jayanta Mukhopadhyay, Sudeshna Sarkar, and Partha Pratim Das. "Fine-grain Cluster Estimation of Land Cover Classes using Landsat 8 Multispectral images." In Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing, pp. 1-9. 2023.
July '23: Chatterjee, Ankita, Jayanta Mukherjee, and Partha Pratim Das. "ImageNet Classification using WordNet Hierarchy." IEEE Transactions on Artificial Intelligence (2023).
July '23: Chatterjee, Ankita, Shankho Subhra Pal, Jayanta Mukhopadhyay, Partha Pratim Das, and Sudeshna Sarkar. "Estimating Cluster numbers in Landsat-8 images using Stability Analysis." In 2023 International Symposium on Signals, Circuits and Systems (ISSCS), pp. 1-4. IEEE, 2023.
October '22: Sadhukhan, Ranajoy, Ankita Chatterjee, Jayanta Mukhopadhyay, and Amit Patra. "Taxonomy Driven Learning Of Semantic Hierarchy Of Classes." In 2022 IEEE International Conference on Image Processing (ICIP), pp. 171-175. IEEE, 2022.
February '22: Chatterjee, Ankita, Jayasree Saha, and Jayanta Mukherjee. "Clustering with multi-layered perceptron." Pattern Recognition Letters 155 (2022): 92-99.
July '21: Chatterjee, Ankita, Jayanta Mukhopadhyay, Subhas Aikat, and Arundhati Misra. "Building Cluster-Class Association for Detecting paddy fields under Semi-Supervised deep learning framework." In 2021 International Symposium on Signals, Circuits and Systems (ISSCS), pp. 1-4. IEEE, 2021.
December '20: Chatterjee, Ankita, Jayanta Mukherjee, Subhas Aikat, and Arundhati Misra. "Semi-supervised classification of paddy fields from dual polarized synthetic aperture radar (sar) images using deep learning." International Journal of Remote Sensing 42, no. 5 (2021): 1867-1892.
September '20: Chatterjee, Ankita, Jayasree Saha, Jayanta Mukhopadhyay, Subhas Aikat, and Arundhati Misra. "Unsupervised Land Cover Classification of Hybrid Polsar Images Using Deep Network." In IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, pp. 1719-1722. IEEE, 2020.
May '20: Chatterjee, Ankita, Jayasree Saha, Jayanta Mukherjee, Subhas Aikat, and Arundhati Misra. "Unsupervised land cover classification of hybrid and dual-polarized images using deep convolutional neural network." IEEE Geoscience and Remote Sensing Letters 18, no. 6 (2020): 969-973.
June '20 - June, '21: Predicting Treatment Response of Lung Cancers Following Curative Chemo-Radiation using Serial Image Analysis.
Description: My main contribution to the project was to build an automated lung tumor segmentation algorithm which could be generalized for all patients. The algorithm should not be highly data dependent and must be able to delineate the tumor with sufficient accuracy using CBCT images.
April '18 - March '20: Polarimetric analysis of SAR images for Segmentation, Classification and Recognition of Objects.
Description: My MS research was directed to their sponsored project and the new deep learning architectures developed were utilized by ISRO. These methods dealt with unsupervised and semi-supervised techniques for land cover classification and detection of paddy fields.
July '16 - August '16: Development of Read-out module for High Resolution Encoder.
Description: The project was a part of my internship in collaboration with Variable Energy Cyclotron Centre (VECC), Department of Atomic Energy (DAE). We worked in a team of two along with a supervisor to guide us. We developed a read-out module for high resolution encoder using Proteus 8 and programmed it in C. This module has been installed in the cyclotron once it was programmed.
PMRF Fellowship for pursuing doctoral degree.
Microsoft Academic Partnership Grant
Nilanjana Paul Gold Medal Memorial Award for the best student, 2017.
Merit Card for Outstanding Performance in Class XII & Class X, 2013 & 2011.
Pytorch, torch.
C, C++, Java, Python.
HTML, CSS, Javascript.
Scikit-learn, OpenCV.
IEEE Student Branch Member, Kharagpur Section, 2021.
Vice President of IEM Student’s Gymkhana, 2016.