Backpropagation-free Network for 3D Test-time Adaptation
This addresses the challenge of domain shifts in real-world 3D systems, offering a more efficient TTA solution, though it appears incremental as it builds on existing TTA concepts.
The paper tackles the problem of computationally heavy and memory-intensive test-time adaptation (TTA) for 3D data by proposing a backpropagation-free method that uses a two-stream architecture and subspace learning, achieving effectiveness on popular benchmarks.
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}.