EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration

arXiv:2403.11026v1 Announce Type: new
Abstract: Transformers have emerged as the state-of-the-art architecture in medical image registration, outperforming convolutional neural networks (CNNs) by addressing their limited receptive fields and overcoming gradient instability in deeper models. Despite their success, transformer-based models require substantial resources for training, including data, memory, and computational power, which may restrict their applicability for end users with limited resources. In particular, existing transformer-based 3D image registration architectures face three critical gaps that challenge their efficiency and effectiveness. Firstly, …

abstract architecture art arxiv cnns computational convolutional neural networks cs.cv data fields gradient image medical memory networks neural networks power registration resources state success training transformer transformers type