Rethinking Attention Gated with Hybrid Dual Pyramid Transformer-CNN for Generalized Segmentation in Medical Imaging

arXiv:2404.18199v1 Announce Type: new
Abstract: Inspired by the success of Transformers in Computer vision, Transformers have been widely investigated for medical imaging segmentation. However, most of Transformer architecture are using the recent transformer architectures as encoder or as parallel encoder with the CNN encoder. In this paper, we introduce a novel hybrid CNN-Transformer segmentation architecture (PAG-TransYnet) designed for efficiently building a strong CNN-Transformer encoder. Our approach exploits attention gates within a Dual Pyramid hybrid encoder. The contributions of this methodology …

abstract architecture architectures arxiv attention cnn computer computer vision cs.cv encoder generalized however hybrid imaging medical medical imaging pyramid segmentation success transformer transformer architecture transformers type vision