# Looking back at Labels: A Class based Domain Adaptation Technique

## TL;DR

This paper introduces an informed adversarial discriminator for multi-class domain adaptation, leveraging class structure information to improve feature transformation and achieve state-of-the-art results.

## Contribution

It proposes a novel informed adversarial discriminator that utilizes class structure information for better domain adaptation in multi-class classification.

## Key findings

- Achieves state-of-the-art results on benchmark datasets.
- Using class structure information improves domain adaptation.
- Detailed analysis confirms the effectiveness of the approach.

## Abstract

In this paper, we solve the problem of adapting classifiers across domains. We consider the problem of domain adaptation for multi-class classification where we are provided a labeled set of examples in a source dataset and we are provided a target dataset with no supervision. In this setting, we propose an adversarial discriminator based approach. While the approach based on adversarial discriminator has been previously proposed; in this paper, we present an informed adversarial discriminator. Our observation relies on the analysis that shows that if the discriminator has access to all the information available including the class structure present in the source dataset, then it can guide the transformation of features of the target set of classes to a more structure adapted space. Using this formulation, we obtain state-of-the-art results for the standard evaluation on benchmark datasets. We further provide detailed analysis which shows that using all the labeled information results in an improved domain adaptation.