Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets

09/20/2019
by   Sinem Aslan, et al.
0

The availability of large-scale data sets is an essential pre-requisite for deep learning based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using low-cost weak annotations has been an attractive research problem in recent years. In this work, we explore the potential of Constrained Dominant Sets (CDS) for generating multi-labeled full mask predictions to train a fully convolutional network (FCN) for semantic segmentation. Our experimental results show that using CDS's yields higher-quality mask predictions compared to methods that have been adopted in the literature for the same purpose.

READ FULL TEXT

page 9

page 10

research
09/11/2023

Learning Semantic Segmentation with Query Points Supervision on Aerial Images

Semantic segmentation is crucial in remote sensing, where high-resolutio...
research
05/25/2017

Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation

Training a Fully Convolutional Network (FCN) for semantic segmentation r...
research
12/21/2019

A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images

Semantic segmentation is the pixel-wise labelling of an image. Since the...
research
06/24/2018

Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data

Semantic segmentation of motion capture sequences plays a key part in ma...
research
07/07/2021

WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations

Compared with tedious per-pixel mask annotating, it is much easier to an...
research
09/21/2016

PixelNet: Towards a General Pixel-level Architecture

We explore architectures for general pixel-level prediction problems, fr...
research
08/12/2020

Pixel-level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation

Corrosion detection on metal constructions is a major challenge in civil...

Please sign up or login with your details

Forgot password? Click here to reset