Multi-task deep learning for image segmentation using recursive approximation tasks

05/26/2020
by   Rihuan Ke, et al.
58

Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard the segmentation problem as a sequence of approximation subproblems that are recursively defined and in increasing levels of approximation accuracy. The subproblems are handled by a framework that consists of 1) a segmentation task that learns from pixel-level ground truth segmentation masks of a small fraction of the images, 2) a recursive approximation task that conducts partial object regions learning and data-driven mask evolution starting from partial masks of each object instance, and 3) other problem oriented auxiliary tasks that are trained with sparse annotations and promote the learning of dedicated features. Most training images are only labeled by (rough) partial masks, which do not contain exact object boundaries, rather than by their full segmentation masks. During the training phase, the approximation task learns the statistics of these partial masks, and the partial regions are recursively increased towards object boundaries aided by the learned information from the segmentation task in a fully data-driven fashion. The network is trained on an extremely small amount of precisely segmented images and a large set of coarse labels. Annotations can thus be obtained in a cheap way. We demonstrate the efficiency of our approach in three applications with microscopy images and ultrasound images.

READ FULL TEXT

page 16

page 17

page 19

page 21

research
06/20/2019

A multi-task U-net for segmentation with lazy labels

The need for labour intensive pixel-wise annotation is a major limitatio...
research
07/15/2020

Automatic Image Labelling at Pixel Level

The performance of deep networks for semantic image segmentation largely...
research
02/16/2021

Uncertainty-based method for improving poorly labeled segmentation datasets

The success of modern deep learning algorithms for image segmentation he...
research
12/06/2021

Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples

Semantic segmentation is a key computer vision task that has been active...
research
09/16/2021

A Multi-Task Cross-Task Learning Architecture for Ad-hoc Uncertainty Estimation in 3D Cardiac MRI Image Segmentation

Medical image segmentation has significantly benefitted thanks to deep l...
research
04/29/2021

Segmentation-grounded Scene Graph Generation

Scene graph generation has emerged as an important problem in computer v...
research
05/27/2019

Unsupervised Object Segmentation by Redrawing

Object segmentation is a crucial problem that is usually solved by using...

Please sign up or login with your details

Forgot password? Click here to reset