A repository for federated domain generalization.

Proposed a novel method for image quality enhancement using diffusion models

VisionCAIR Zero-Shot Learning Research

Domain Adaptation methods on Office31

Learning to Generalize towards Unseen Domains via a Content-Aware Style Invariant Framework for Disease Detection from Chest X-rays

Course work project for IFT6759 - WILDS - Distribution shifts in wilds - iwildcam

Code for the control+shift paper, where a method for generating general datasets with a controllable amount of distribution shift was proposed. Presented at the ECCV'24 "Synthetic Data for Computer Vision" workshop.

FLUXNET benchmark

[AAAI 2026] Official implementation of the paper "Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation"

Official implementation of the TMLR paper: An Analysis of Model Robustness across Concurrent Distribution Shifts.

Project Page (ObjectDR)

This work has been accepted by AAAI-26.

All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt Tuning

project to enable neural network feature space modeling using probabilistic and geometric models (KDE, Diffusion Maps, Convex Hulls, etc) and to run domain generalization hypothesis testing (more options to come) - meant to encapsulate most of the evaluation code used in my thesis in a clean, modular structure

code for "Learning Generalizable Part-based Feature Representation for 3D Point Clouds" (NeurIPS 2022)

An unofficial implementation of Frustratingly Simple Domain Generalization via Image Stylization

This repository contains the code associated with the master's thesis "Invariance and Generalization for Classification" written by Linus Kühne at ETH Zurich in 2024.

Data loader and solution method for the DCASE 2024 Challenge Task1

The code for magnification generalization for the histopathology image embedding

Domain generalization on Aspect Based Sentiment Analysis (ABSA) task via utilizing noisy student architecture.