Autofocus Layer for Semantic Segmentation

Abstract

We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing. Autofocus layers adaptively change the size of the effective receptive field based on the processed context to generate more powerful features. This is achieved by parallelising multiple convolutional layers with different dilation rates, combined by an attention mechanism that learns to focus on the optimal scales driven by context. By sharing the weights of the parallel convolutions we make the network scale-invariant, with only a modest increase in the number of parameters. The proposed autofocus layer can be easily integrated into existing networks to improve a model's representational power. We evaluate our models on the challenging tasks of multi-organ segmentation in pelvic CT and brain tumor segmentation in MRI and achieve very promising performance.

arXiv commentPublished on MICCAI 2018

References in corpus (3)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Multi-Scale Context Aggregation by Dilated Convolutions
• CNN-based Segmentation of Medical Imaging Data

Cited by in corpus (5)

• A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
• A review: Deep learning for medical image segmentation using multi-modality fusion
• Brain segmentation based on multi-atlas guided 3D fully convolutional network ensembles
• Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology
• BI-RADS-Net: An Explainable Multitask Learning Approach for Cancer Diagnosis in Breast Ultrasound Images