Abstract

Convolutional neural networks (CNNs) such as encoder–decoder CNNs have increasingly been employed for semantic image segmentation at the pixel‐level requiring pixel‐level training labels, which are rarely available in real‐world scenarios. In practice, weakly annotated training data at the image patch level are often used for pixel‐level segmentation tasks, requiring further processing to obtain accurate results, mainly because the translation invariance of the CNN‐based inference can turn into an impeding property leading to segmentation results of coarser spatial granularity compared with the original image. However, the inherent uncertainty in the segmented image and its relationships to translation invariance, CNN architecture, and classification scheme has never been analysed from an explicitly spatial perspective. Therefore, the authors propose measures to spatially visualise and assess class …

Date

January 1, 1970

Authors

Johannes H Uhl, Stefan Leyk, Yao‐Yi Chiang, Weiwei Duan, Craig A Knoblock

Journal

IET Image Processing

Volume

12

Issue

11

Pages

2084-2091

Publisher

The Institution of Engineering and Technology