Saved in:
Bibliographic Details
Main Authors: Qu, Sanqing, Zou, Tianpei, Röhrbein, Florian, Lu, Cewu, Chen, Guang, Tao, Dacheng, Jiang, Changjun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.14410
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912501555265536
author Qu, Sanqing
Zou, Tianpei
Röhrbein, Florian
Lu, Cewu
Chen, Guang
Tao, Dacheng
Jiang, Changjun
author_facet Qu, Sanqing
Zou, Tianpei
Röhrbein, Florian
Lu, Cewu
Chen, Guang
Tao, Dacheng
Jiang, Changjun
contents Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm to discern between target classes, complemented by a local k-NN clustering strategy to mitigate negative transfer. Despite the effectiveness, the inherent closed-set source architecture leads to uniform treatment of "unknown" data, impeding the identification of distinct "unknown" categories. To address this, we evolve GLC to GLC++, integrating a contrastive affinity learning strategy. We examine the superiority of GLC and GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by 16.8\% and 18.9\% in H-score on VisDA, respectively. GLC++ enhances the novel category clustering accuracy of GLC by 4.1\% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies. The code is available at https://github.com/ispc-lab/GLC-plus.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14410
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
Qu, Sanqing
Zou, Tianpei
Röhrbein, Florian
Lu, Cewu
Chen, Guang
Tao, Dacheng
Jiang, Changjun
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm to discern between target classes, complemented by a local k-NN clustering strategy to mitigate negative transfer. Despite the effectiveness, the inherent closed-set source architecture leads to uniform treatment of "unknown" data, impeding the identification of distinct "unknown" categories. To address this, we evolve GLC to GLC++, integrating a contrastive affinity learning strategy. We examine the superiority of GLC and GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by 16.8\% and 18.9\% in H-score on VisDA, respectively. GLC++ enhances the novel category clustering accuracy of GLC by 4.1\% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies. The code is available at https://github.com/ispc-lab/GLC-plus.
title GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2403.14410