Siladittya Manna

Post-Doc RA, VCL Lab @iiscbangalore || SRA @hkbaptistu || Ph.D.(CS) @ISIKolkata || Alum.@iiest_s || FedML, CV, Self-SL, Med IA || ||

[Siladittya Manna @sadimanna]

🌟 New Public Dataset Release! 🌟

We’re thrilled to announce the publication of MOGaMBO—a groundbreaking Multi-Organ Gynaecological MRI Dataset for advancing AI-driven medical image analysis for cervical cancer brachytherapy research 🏥💡

[Ponnurangam Kumaraguru “PK” @ponguru]

📚 Fantastic #ANRFAmbassador paper reading @MSFTResearch #Bengaluru 30+ participants across UG, Master’s, PhD, faculty & industry. 🔥 Great presentations + questions! Thanks @KodaliPrashant & Microsoft Research for hosting! 🚀 #ANRFSabbatical #ProfGiri /c @ANRFIndia @shivkuma_k

[Francis Bach @BachFrancis]

Overwhelmed by the variance of means of exponentials? This blog post is meant for you.

As a bonus, a spectral closed-form formula for (approximate) multinomial logistic regression.

https://t.co/y1MqyDdszR

[Siladittya Manna @sadimanna]

Looking forward to presenting our work and engaging with the community. Grateful for all the support and collaboration along the way!

#ICIP2026 #ComputerVision #ImageProcessing

[Siladittya Manna @sadimanna]

Thrilled to share that our paper, “Reliability-Aware Weighted Multi-Scale Spatio-Temporal Maps for Heart Rate Monitoring,” has been accepted at ICIP 2026! 🎉

Congrats to Arpan, Rakesh (@RakeshD24137483), and Prof. Umapada Pal

#ICIP2026 #ImageProcessing

[Avi Chawla @_avichawla]

You are in an ML interview.

Your interviewer asks: "Why is Kernel Trick called a Trick?"

Here's how to answer (with simple maths):

[Siladittya Manna @sadimanna]

Just a personal opinion:

Two best introductory materials for Domain Adaptation:

A theory of learning from different domains
https://t.co/3UXe9BMAgJ

An introduction to domain adaptation and transfer learning
https://t.co/fRaR4AdtFN

Let me know of other ones!

[Siladittya Manna @sadimanna]

Try out this medical image viewer I tried building with Cursor as a side project

https://t.co/obqo2BZ1Fo

Supports nii, nii.gz, dcm, png, npy, jpg inputs

It can also process multiple files or folder inputs of 2D images into 3D data

[Siladittya Manna @sadimanna]

The only thing I have left in my life to show is this GitHub page

https://t.co/9Ud0t4d1Pa

[Paweł Huryn @PawelHuryn]

I see abstract AI agent architectures everywhere.

But no one explains how to build them in practice.

Here's a practical guide to doing it with n8n: 🧵

[Siladittya Manna @sadimanna]

Thank you to everyone who has been part of this journey. Onward and upward! 🚀

[Siladittya Manna @sadimanna]

🎉 Exciting News! 🎓

I am thrilled to announce that I have officially been awarded my PhD in Computer Science from the Indian Statistical Institute, Kolkata, after I successfully defended my thesis titled "Self-Supervised Learning and its Applications in Medical Image Analysis".

[Siladittya Manna @sadimanna]

I am incredibly grateful to my supervisor Prof. Umapada Pal, mentor Dr. Saumik Bhattacharya (Indian Institute of Technology, Kharagpur), labmates, friends, and family for their unwavering support and encouragement throughout this journey.

[Siladittya Manna @sadimanna]

Also available on Kaggle:

https://t.co/8typq6SINo

[Siladittya Manna @sadimanna]

🌟 New Public Dataset Release! 🌟

We’re thrilled to announce the publication of MOGaMBO—a groundbreaking Multi-Organ Gynaecological MRI Dataset for advancing AI-driven medical image analysis for cervical cancer brachytherapy research 🏥💡

[Siladittya Manna @sadimanna]

#MedicalImaging #AIinHealthcare #Brachytherapy #OpenScience #CervicalCancer #DataScience #OncologyResearch