# Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss

## TL;DR

This paper introduces a deep learning framework for unsupervised domain adaptation that uses feature whitening for domain alignment and a novel Min-Entropy Consensus loss to leverage unlabeled data, achieving state-of-the-art results.

## Contribution

It unifies domain alignment via feature whitening with a new loss function that effectively utilizes unlabeled target data without extensive hyper-parameter tuning.

## Key findings

- Improves performance on digit classification datasets.
- Achieves state-of-the-art results in object recognition tasks.
- Effectively leverages unlabeled data with minimal hyper-parameters.

## Abstract

A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain alignment layers which implement feature whitening for the purpose of matching source and target feature distributions. Additionally, we leverage the unlabeled target data by proposing the Min-Entropy Consensus loss, which regularizes training while avoiding the adoption of many user-defined hyper-parameters. We report results on publicly available datasets, considering both digit classification and object recognition tasks. We show that, in most of our experiments, our approach improves upon previous methods, setting new state-of-the-art performances.