ACNN block

2000년 도입 · 논문 2편에서 사용

Atrous Convolution Neural Network (ACNN), as a pooling-free network structure, is proposed to achieve full-resolution feature processing using a theoretically optimal dilation setting for a larger receptive field, even with fewer parameters. Compared to other techniques, it can achieve higher segmentation Intersection over Union (IoU) and much less trainable parameters and model sizes, indicating the benefit of full-resolution feature maps in feature processing.

출처: ACNN: a Full Resolution DCNN for Medical Image Segmentation

소개 논문: ACNN: a Full Resolution DCNN for Medical Image Segmentation