Trust Your Good Friends : Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering
Yang, Shiqi (Centre de Visió per Computador)
Wang, Yaxing (Nankai University. College of Computer Science)
Weijer, Joost van de (Centre de Visió per Computador)
Herranz, Luis (Universitat Autònoma de Barcelona)
Jui, Shangling (Huawei Kirin Solution)
Yang, Jian (Nankai University. College of Computer Science)

Fecha:	2023
Resumen:	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.
Ayudas:	Agencia Estatal de Investigación PID2022-143257NB-I00 Agencia Estatal de Investigación PID2021-128178OB-I00 Ministerio de Ciencia e Innovación RYC2019-027020-I
Nota:	Altres ajuts: CERCA Programme/Generalitat de Catalunya
Derechos:	Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió acceptada per publicar
Materia:	Domain adaptation ; Source-free domain adaptation
Publicado en:	IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, Issue 12 (December 2023) , p. 15883-15895, ISSN 1939-3539

DOI: 10.1109/TPAMI.2023.3310791

Postprint

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados