Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration
arXiv:2407.19274 · doi:10.1007/978-3-031-73480-9_7
Abstract
Our findings indicate that adopting "advanced" computational elements fails to significantly improve registration accuracy. Instead, well-established registration-specific designs offer fair improvements, enhancing results by a marginal 1.5\% over the baseline. Our findings emphasize the importance of rigorous, unbiased evaluation and contribution disentanglement of all low- and high-level registration components, rather than simply following the computer vision trends with "more advanced" computational blocks. We advocate for simpler yet effective solutions and novel evaluation metrics that go beyond conventional registration accuracy, warranting further research across diverse organs and modalities. The code is available at \url{https://github.com/BailiangJ/rethink-reg}.
WBIR 2024 Workshop on Biomedical Imaging Registration
References in corpus (5)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- TransMorph: Transformer for unsupervised medical image registration
- Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration
- Non-iterative Coarse-to-fine Registration based on Single-pass Deep Cumulative Learning
- Attention-aware non-rigid image registration for accelerated MR imaging