A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
- PDF / 6,872,459 Bytes
- 24 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 188 Views
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains Lyndon Chan1
· Mahdi S. Hosseini1
· Konstantinos N. Plataniotis1
Received: 20 December 2019 / Accepted: 18 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Recently proposed methods for weakly-supervised semantic segmentation have achieved impressive performance in predicting pixel classes despite being trained with only image labels which lack positional information. Because image annotations are cheaper and quicker to generate, weak supervision is more practical than full supervision for training segmentation algorithms. These methods have been predominantly developed to solve the background separation and partial segmentation problems presented by natural scene images and it is unclear whether they can be simply transferred to other domains with different characteristics, such as histopathology and satellite images, and still perform well. This paper evaluates state-of-the-art weaklysupervised semantic segmentation methods on natural scene, histopathology, and satellite image datasets and analyzes how to determine which method is most suitable for a given dataset. Our experiments indicate that histopathology and satellite images present a different set of problems for weakly-supervised semantic segmentation than natural scene images, such as ambiguous boundaries and class co-occurrence. Methods perform well for datasets they were developed on, but tend to perform poorly on other datasets. We present some practical techniques for these methods on unseen datasets and argue that more work is needed for a generalizable approach to weakly-supervised semantic segmentation. Our full code implementation is available on GitHub: https://github.com/lyndonchan/wsss-analysis. Keywords Weakly supervised semantic segmentation · Self-supervised Learning · Natural imaging · Digital pathology · Satellite imaging · Deep learning · Convolutional neural network
1 Introduction Multi-class semantic segmentation aims to predict a discrete semantic class for every pixel in an image. This is useful as an attention mechanism: by ignoring the irrelevant parts of the image, only relevant parts are retained for further analysis, such as faces and human parts (Prince 2012a). Semantic segmentation is also useful for changing the pixels of the image into higher-level representations that are more meaningful Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11263-020-01373-4) contains supplementary material, which is available to authorized users.
B B 1
Lyndon Chan [email protected] Mahdi S. Hosseini [email protected] The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada
for further analysis, such as object locations, shapes, sizes, textures, poses, or actions (Shapiro and Stockman 2000). Oftentimes, semantic segmentation is used when simply predicting a bounding box around t
Data Loading...
