Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering

TL;DR

This paper introduces a source-free domain adaptation method that leverages the intrinsic clustering structure of target data through reciprocal neighborhood clustering, achieving state-of-the-art results without source data access.

Contribution

The method uniquely utilizes reciprocal neighborhood clustering and local density to adapt models in source-free domain adaptation scenarios.

Findings

Achieves state-of-the-art performance on multiple datasets.

Effectively captures target data structure for better adaptation.

Outperforms existing source-free domain adaptation methods.

Abstract

Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g. due to data privacy or intellectual property). In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. Our method is based on the observation that target data, which might not align with the source domain classifier, still forms clear clusters. We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity. We observe that higher affinity should be assigned to reciprocal neighbors. To aggregate information with more context, we consider expanded neighborhoods with small affinity values. Furthermore, we consider the density around each target sample, which can alleviate the negative impact of potential outliers. In the experimental results we verify that the inherent structure of the target features is an important source of information for domain adaptation. We demonstrate that this local structure can be efficiently captured by considering the local neighbors, the reciprocal neighbors, and the expanded neighborhood. Finally, we achieve state-of-the-art performance on several 2D image and 3D point cloud recognition datasets.