Backpropagation-free Network for 3D Test-time Adaptation
Date
2024
Authors
Wang, Y.
Cheraghian, A.
Hayder, Z.
Hong, J.
Ramasinghe, S.
Rahman, S.
Ahmedt-Aristizabal, D.
Li, X.
Petersson, L.
Harandi, M.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2024, pp.23231-23241
Statement of Responsibility
Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li, Lars Petersson, Mehrtash Harandi
Conference Name
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (16 Jun 2024 - 22 Jun 2024 : Seattle, United States)
Abstract
Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test- Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches to handle this. Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data. Our model uses a two-stream architecture to maintain knowledge about the source domain as well as complementary target-domain-specific information. The backpropagation-free property of our model helps address the well-known forgetting prob-lem and mitigates the error accumulation issue. The pro-posed method also eliminates the need for the usually noisy process of pseudo-labeling and reliance on costly self-supervised training. Moreover, our method leverages sub-space learning, effectively reducing the distribution vari-ance between the two domains. Furthermore, the source-domain-specific and the target-domain-specific streams are aligned using a novel entropy-based adaptive fusion strat-egy. Extensive experiments on popular benchmarks demon-strate the effectiveness of our method.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2024 IEEE.