Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration
Not on the map. Why?
Abstract (arXiv)
Combinatorial explosion problem caused by dual inputs presents a critical challenge in Deformable Medical Image Registration (DMIR). Since DMIR processes two images simultaneously as input, the combination relationships between features has grown exponentially, ultimately the model considers more interfering features during the feature modeling process. Introducing dynamics in the receptive fields and weights of the network enable the model to eliminate the interfering features combination and model the potential feature combination relationships. In this paper, we propose the Dynamic Stream Network (DySNet), which enables the receptive fields and weights to be dynamically adjusted. This ultimately enables the model to ignore interfering feature combinations and model the potential feature relationships. With two key innovations: 1) Adaptive Stream Basin (AdSB) module dynamically adjusts the shape of the receptive field, thereby enabling the model to focus on the feature relationships with greater correlation. 2) Dynamic Stream Attention (DySA) mechanism generates dynamic weights to search for more valuable feature relationships. Extensive experiments have shown that DySNet consistently outperforms the most advanced DMIR methods, highlighting its outstanding generalization ability. Our code will be released on the website: https://github.com/ShaochenBi/DySNet.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 48 references that are in the map. First posted on arXiv 22 Dec 2025.
Builds on
26 of 48 references.
References · 26
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2017Non-local Neural Networkscited by 2,290
- 2014How transferable are features in deep neural networks?cited by 1,216
- 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
- 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
- 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
14 more
- 2022Vision Transformer with Deformable Attentioncited by 293
- 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
- 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
- 2019Automated brain extraction of multi-sequence MRI using artificial neural networkscited by 133
- 2019Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challengecited by 100
- 2018Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registrationcited by 90
- 2021ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registrationcited by 87
- 2020An automatic multi-tissue human fetal brain segmentation benchmark using the Fetal Tissue Annotation Datasetcited by 59
- 2022XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attentioncited by 46
- 2022U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?cited by 40
- 2018Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registrationcited by 23
- 2018Deep Nets: What have they ever done for Vision?cited by 23
- 2023Adaptive Correspondence Scoring for Unsupervised Medical Image Registrationcited by 9
- 2025SACB-Net: Spatial-awareness Convolutions for Medical Image Registrationcited by 2
Built on by
Not cited yet.