A multi-task U-net for segmentation with lazy labels
Preprint
Abstract
The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for image segmentation. In this paper, we propose a deep convolutional neural network for multi-class segmentation that circumvents this problem by being trainable on coarse data labels combined with only a very small number of images with pixel-wise annotations. We call this new labelling strategy 'lazy' labels. Image segmentation is then stratified into three connected tasks: rough detection of class instances, separation of wrongly connected objects without a clear boundary, and pixel-wise segmentation to find the accurate boundaries of each object. These problems are integrated into a multitask learning framework and the model is trained end-to-end in a semi-supervised fashion. The method is applied on a dataset of food microscopy images. We show that the model gives accurate segmentation results even if exact boundary labels are missing for a majority of the annotated data. This allows more flexibility and efficiency for training deep neural networks that are data hungry in a practical setting where manual annotation is expensive, by collecting more lazy (rough) annotations than precisely segmented images.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks2019
- Coarse-to-Fine Semantic Segmentation From Image-Level LabelsIEEE Transactions on Image Processing, 2019
- FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference2019
- Coarse-to-fine volumetric segmentation of teeth in cone-beam ct2019
- Saliency guided deep network for weakly-supervised image segmentationPattern Recognition Letters, 2019
- Weakly supervised 3D deep learning for breast cancer classification and localization of the lesions in MR imagesJournal of Magnetic Resonance Imaging, 2019
- A Novel Weakly Supervised Multitask Architecture for Retinal Lesions Segmentation on Fundus ImagesIEEE Transactions on Medical Imaging, 2019
- Revealing the microstructural stability of a three-phase soft solid (ice cream) by 4D synchrotron X-ray tomographyJournal of Food Engineering, 2018
- Synchrotron X-ray tomographic quantification of microstructural evolution in ice cream – a multi-phase soft solidRSC Advances, 2017
- What’s the Point: Semantic Segmentation with Point Supervision2016