[MedIA Best Paper Award] Official implementation of MedIA paper "BayeSeg: Bayesian Modelling for Medical Image Segmentation with Interpretable Generalizability"

The official implementation of "Joint Modeling of Image and Label Statistics for Enhancing Model Generalizability of Medical Image Segmentation" via Pytorch

This is the code of ICLR 2022 Oral paper 'Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization'.

[ICML'21] Estimate the accuracy of the classifier in various environments through self-supervision

Model Generalization on CIFAR-10 Dataset, accuracy higher than 91% on test data

subMFL: Compatible subModel Generation for Federated Learning in Device Heterogeneous Environment

Implemented hyperparameter fine-tuning experiments for the M2CRL (Multi-view Masked Contrastive Representation Learning) framework to improve model generalization and downstream performance through systematic training and evaluation.

This project implements the classical LeNet-5 CNN for MNIST digit classification using PyTorch. It covers a complete pipeline from data preprocessing to deployment. The model achieves ~98.8% test accuracy, showing the strong effectiveness of early CNN architectures for image classification.

Interpretable classical-ML smishing/scam detector — quantifies how Western-trained models fail on India-specific scams (UPI/KYC/FASTag) and fixes the gap with a small India sample. Fully explainable, offline W-vs-A demo. No deep learning.