GitHub

fastapi-example

Practical Clean Architecture backend example built with FastAPI. No stateful globals (DI), low coupling (DIP), tactical DDD, CQRS, proper UoW usage. REST API, per ...
note

How data aggregation that used to take 30 minutes to an hour now finishes in an instant | Real-world examples of changing work with AI #3

I am not an AI consultant. I am the president of a company with just over 20 employees that sells paint online in Osaka. I cannot program. I have no specialized IT knowledge. In this series, I will ...
IEEE

Toward Secure Weighted Aggregation for Privacy-Preserving Federated Learning

Abstract: Privacy-preserving federated learning can protect the privacy of model gradients/parameters in the model aggregation phase. Most existing schemes only ...
IEEE

Batch-Aggregate: Efficient Aggregation for Private Federated Learning in VANETs

Abstract: Federated learning (FL) in Vehicular Ad-hoc Networks (VANETs) enables vehicles to collaboratively train machine learning models by aggregating local gradients without revealing the training ...
GitHub

Optimal Transport Aggregation for Visual Place Recognition

We introduce DINOv2 SALAD, a Visual Place Recognition model that achieves state-of-the-art results on common benchmarks. We introduce two main contributions: Using a finetuned DINOv2 encoder to get ...