Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds Article Swipe

MAKE IMPACT

Zicheng Wang , Zhen Zhao , Yiming Wu , Luping Zhou , Dong Xu · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2311.16474

Unsupervised domain adaptation (UDA) is a critical challenge in the field of point cloud analysis. Previous works tackle the problem either by feature extractor adaptation to enable a shared classifier to distinguish domain-invariant features, or by classifier adaptation to evolve the classifier to recognize target-styled source features to increase its adaptation ability. However, by learning domain-invariant features, feature extractor adaptation methods fail to encode semantically meaningful target-specific information, while classifier adaptation methods rely heavily on the accurate estimation of the target distribution. In this work, we propose a novel framework that deeply couples the classifier and feature extractor adaption for 3D UDA, dubbed Progressive Classifier and Feature Extractor Adaptation (PCFEA). Our PCFEA conducts 3D UDA from two distinct perspectives: macro and micro levels. On the macro level, we propose a progressive target-styled feature augmentation (PTFA) that establishes a series of intermediate domains to enable the model to progressively adapt to the target domain. Throughout this process, the source classifier is evolved to recognize target-styled source features (\ie, classifier adaptation). On the micro level, we develop an intermediate domain feature extractor adaptation (IDFA) that performs a compact feature alignment to encourage the target-styled feature extraction gradually. In this way, PTFA and IDFA can mutually benefit each other: IDFA contributes to the distribution estimation of PTFA while PTFA constructs smoother intermediate domains to encourage an accurate feature alignment of IDFA. We validate our method on popular benchmark datasets, where our method achieves new state-of-the-art performance. Our code is available at https://github.com/xiaoyao3302/PCFEA.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2311.16474

PDF

https://arxiv.org/pdf/2311.16474

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4389156658

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4389156658

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2311.16474

Digital Object Identifier

Title

Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-11-27

Full publication date if available

Authors

Zicheng Wang, Zhen Zhao, Yiming Wu, Luping Zhou, Dong Xu

List of authors in order

Landing page

https://arxiv.org/abs/2311.16474

Publisher landing page

PDF URL

https://arxiv.org/pdf/2311.16474

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2311.16474

Direct OA link when available

Concepts

Computer science, Classifier (UML), Discriminative model, Artificial intelligence, Domain adaptation, Feature extraction, Machine learning, Extractor, Benchmark (surveying), Pattern recognition (psychology), Feature learning, Feature (linguistics), Engineering, Geography, Linguistics, Geodesy, Philosophy, Process engineering

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload