Hi there 👋. I am Sayak (সায়ক) Paul. I am a Machine Learning Engineer at Carted. Know more about me from here.
This site is built with fastpages, an easy to use blogging platform with extra features for Jupyter Notebooks.
My external articles and other publishing engagements (like books, liveProjects, etc.) are listed here. Decks from my speaking engagements are listed here. Interviews are here.
News
- New work with Pin-Yu Chen (IBM Research): Vision Transformers are Robust Learners. Accepted to AAAI 2022.
- New work with Siddha Ganju (NVIDIA): Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning. This work is based on our winning solution (first runners-up) submitted to this competition organized by the NASA Impact team. We also made it to four NeurIPS 2021 workshops: AI for Science: Mind the Gaps, Tackling Climate Change with Machine Learning, Women in ML, and Machine Learning and the Physical Sciences.
- Accepted to the Oxford ML Summer School.
- New project with Aritra Roy Gosthipaty on probing the representations learned by ViTs. Code, models, tutorial, interactive demos, visuals are available here.
- Implemented Swin Transformers in TensorFlow and ported the original pre-trained parans into them. Code, pre-trained TF models, notebooks are available here.
To know about my projects, please refer to my GitHub profile.
Apart from the following blog posts, I try to contribute to other platforms in the form of writing. Please refer here for more details.
