A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation

08/17/2021
by   Xi Liu, et al.
12

Image co-segmentation has attracted a lot of attentions in computer vision community. In this paper, we propose a new approach to image co-segmentation through introducing the dense connections into the decoder path of Siamese U-net and presenting a new edge enhanced 3D IOU loss measured over distance maps. Considering the rigorous mapping between the signed normalized distance map (SNDM) and the binary segmentation mask, we estimate the SNDMs directly from original images and use them to determine the segmentation results. We apply the Siamese U-net for solving this problem and improve its effectiveness by densely connecting each layer with subsequent layers in the decoder path. Furthermore, a new learning loss is designed to measure the 3D intersection over union (IOU) between the generated SNDMs and the labeled SNDMs. The experimental results on commonly used datasets for image co-segmentation demonstrate the effectiveness of our presented dense structure and edge enhanced 3D IOU loss of SNDM. To our best knowledge, they lead to the state-of-the-art performance on the Internet and iCoseg datasets.

READ FULL TEXT

page 2

page 3

page 5

page 6

research
12/02/2018

MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation

Radiologist is "doctor's doctor", biomedical image segmentation plays a ...
research
05/11/2020

Medical Image Segmentation Using a U-Net type of Architecture

Deep convolutional neural networks have been proven to be very effective...
research
08/31/2019

Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions

In recent years, deep learning-based networks have achieved state-of-the...
research
03/18/2023

Lung segmentation with NASNet-Large-Decoder Net

Lung cancer has emerged as a severe disease that threatens human life an...
research
09/10/2018

Interactive Binary Image Segmentation with Edge Preservation

Binary image segmentation plays an important role in computer vision and...
research
03/19/2023

Uncertainty Driven Bottleneck Attention U-net for OAR Segmentation

Organ at risk (OAR) segmentation in computed tomography (CT) imagery is ...
research
04/06/2021

First arrival picking using U-net with Lovasz loss and nearest point picking method

We proposed a robust segmentation and picking workflow to solve the firs...

Please sign up or login with your details

Forgot password? Click here to reset