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 problem and mitigates the error accumulation issue. The proposed method also eliminates the need for the usually noisy process of pseudo-labeling and reliance on costly self-supervised training. Moreover, our method leverages subspace learning, effectively reducing the distribution variance between the two domains. Furthermore, the source-domain-specific and the target-domain-specific streams are aligned using a novel entropy-based adaptive fusion strategy. Extensive experiments on popular benchmarks demonstrate the effectiveness of our method. The code will be available at \url{https://github.com/abie-e/BFTT3D}.
@article{arxiv.2403.18442,
title = {Backpropagation-free Network for 3D Test-time Adaptation},
author = {Yanshuo Wang and Ali Cheraghian and Zeeshan Hayder and Jie Hong and Sameera Ramasinghe and Shafin Rahman and David Ahmedt-Aristizabal and Xuesong Li and Lars Petersson and Mehrtash Harandi},
journal= {arXiv preprint arXiv:2403.18442},
year = {2024}
}