DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks

05/25/2016
by   Martin Rajchl, et al.
0

In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naive approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.

READ FULL TEXT

page 3

page 5

page 6

page 7

research
05/29/2021

Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks

Accurate segmentation for medical images is important for clinical diagn...
research
03/03/2020

Towards Noise-resistant Object Detection with Noisy Annotations

Training deep object detectors requires significant amount of human-anno...
research
07/02/2017

Deep GrabCut for Object Selection

Most previous bounding-box-based segmentation methods assume the boundin...
research
04/22/2019

Detecting retail products in situ using CNN without human effort labeling

CNN is a powerful tool for many computer vision tasks, achieving much be...
research
09/09/2019

Connected Assembly and Reconfiguration by Finite Automata

We consider methods for connected reconfigurations by finite automate in...
research
11/12/2015

ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks

This paper aims to classify and locate objects accurately and efficientl...
research
09/21/2023

2DDATA: 2D Detection Annotations Transmittable Aggregation for Semantic Segmentation on Point Cloud

Recently, multi-modality models have been introduced because of the comp...

Please sign up or login with your details

Forgot password? Click here to reset