Dr. Avisek Gupta

Post Doctoral Fellow, IAI – TCG CREST


I am currently working in the areas of unsupervised data clustering and weakly supervised learning. In the area of data clustering, I have previously focused on factors affecting the performance of center-based clustering methods – the features used, the distance metric that can be learnt, the number of clusters that can be identified, etc. Recently I have been interested in the general area of weakly supervised learning, and how low-effort supervision from experts can be provided to guide the learning process of a statistical model.


I completed my Ph.D. degree in Computer Science at the Indian Statistical Institute, Kolkata, in November 2021. I received my B.Tech. and M.E. degrees in Computer Science & Engineering from the West Bengal University of Technology (currently the Maulana Abul Kalam Azad University of Technology, West Bengal) in 2012 and Jadavpur University in 2014, respectively. I worked on a SERB project on Bengali document querying, clustering and summarization from July 2014 to May 2015 at Jadavpur University. Prior to joining TCG Crest, I worked as a Visiting Scientist at the Electronics and Communication Sciences Unit, Indian Statistical Institute Kolkata, from December 2021 to March 2022.


I was an organizing chair for the recent Winter School on Deep Learning 2022, organized by ECSU at the Indian Statistical Institute, Kolkata.

I have been a Teaching Assistant for the following courses:

  • Computer Vision (Second Year M.Tech. CS, ISI Kolkata) 2019-20, with Dr. Swagatam Das.
  • Computing for Data Sciences (First Year PGDBA, ISI Kolkata) 2018-2019, with Dr. Swagatam Das. The course website can be viewed from this [Link].


  1. Avisek Gupta and Swagatam Das, “Improved Efficient Model Selection for Sparse Hard and Fuzzy Center-Based Clustering”, Information Sciences, vol. 590, pp. 29-44, 2022. DOI:10.1016/j.ins.2021.12.070.
  2. Avisek Gupta and Swagatam Das, “Transfer Clustering Using a Multiple Kernel Metric Learned Under Multi-Instance Weak Supervision”, IEEE Transactions On Emerging Topics In Computational Intelligence, 2021. DOI:10.1109/TETCI.2021.3110526.
  3. Avisek Gupta, Shounak Datta, and Swagatam Das, “Fuzzy Clustering to Identify Clusters at Different Levels of Fuzziness: An Evolutionary Multiobjective Optimization Approach”, IEEE Transactions on Cybernetics, vol. 51 (5), pp. 2601–2611, 2019. DOI:10.1109/TCYB.2019.2907002.
  4. Avisek Gupta, Shounak Datta, Swagatam Das, “Fast automatic estimation of the number of clusters from the minimum inter-center distance for k-means clustering”, Pattern Recognition Letters, vol. 116, pp. 72-79, 2018. DOI:10.1016/j.patrec.2018.09.003.
  5. Avisek Gupta, Swagatam Das, “On the Unification of k-Harmonic Means and Fuzzy c-Means Clustering Problems under Kernelization”, In the Proceedings of the Ninth International Conference on Advances in Pattern Recognition (ICAPR-2017), pp. 386-391, 2017. DOI:10.1109/ICAPR.2017.8593078.

Contact: avisek.gupta@tcgcrest.com (e-mail)