Implantable Adaptive Cells: differentiable architecture search to improve the performance of any trained U-shaped network

arXiv:2405.03420v1 Announce Type: new
Abstract: This paper introduces a novel approach to enhance the performance of pre-trained neural networks in medical image segmentation using Neural Architecture Search (NAS) methods, specifically Differentiable Architecture Search (DARTS). We present the concept of Implantable Adaptive Cell (IAC), small but powerful modules identified through Partially-Connected DARTS, designed to be injected into the skip connections of an existing and already trained U-shaped model. Our strategy allows for the seamless integration of the IAC into the pre-existing …

abstract architecture arxiv cells concept cs.cv differentiable iac image medical nas network networks neural architecture search neural networks novel paper performance search segmentation small type