← Search

Sara Romiti

2 accepted papers

2022

Okapi: Generalising Better by Making Statistical Matches Match

NeurIPS 2022accept

We propose Okapi, a simple, efficient, and general method for robust semi-supervised learning based on online statistical matching. Our method uses a nearest-neighbours-based matching procedure to generate cross-domain views for a consistency loss, while eliminating statistical outliers. In order to…

2022

RealPatch: A Statistical Matching Framework for Model Patching with Real Samples

ECCV 2022poster

"Machine learning classifiers are typically trained to minimise the average error across a dataset. Unfortunately, in practice, this process often exploits spurious correlations caused by subgroup imbalance within the training data, resulting in high average performance but highly variable performan…