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. The code will be available at https://github.com/abie-e/BFTT3D.
| Original language | English |
|---|---|
| Pages (from-to) | 23231-23241 |
| Number of pages | 11 |
| Journal | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
| DOIs | |
| Publication status | Published - 2024 |
| Event | 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Seattle, United States Duration: 16 Jun 2024 → 22 Jun 2024 |
Fingerprint
Dive into the research topics of 'Backpropagation-free Network for 3D Test-time Adaptation'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver