FCIoU: A Targeted Approach for Improving Minority Class Detection in Semantic Segmentation Systems
-
Published:2023-11-23
Issue:4
Volume:5
Page:1746-1759
-
ISSN:2504-4990
-
Container-title:Machine Learning and Knowledge Extraction
-
language:en
-
Short-container-title:MAKE
Author:
Plangger Jonathan1, Atia Mohamed2, Chaoui Hicham1ORCID
Affiliation:
1. Department of Electronics (DOE), Carleton University, Ottawa, ON K1S 5B6, Canada 2. Department of Systems and Communication, Carleton University, Ottawa, ON K1S 5B6, Canada
Abstract
In this paper, we present a comparative study of modern semantic segmentation loss functions and their resultant impact when applied with state-of-the-art off-road datasets. Class imbalance, inherent in these datasets, presents a significant challenge to off-road terrain semantic segmentation systems. With numerous environment classes being extremely sparse and underrepresented, model training becomes inefficient and struggles to comprehend the infrequent minority classes. As a solution to this problem, loss functions have been configured to take class imbalance into account and counteract this issue. To this end, we present a novel loss function, Focal Class-based Intersection over Union (FCIoU), which directly targets performance imbalance through the optimization of class-based Intersection over Union (IoU). The new loss function results in a general increase in class-based performance when compared to state-of-the-art targeted loss functions.
Funder
NSERC Discovery research grant
Subject
Artificial Intelligence,Engineering (miscellaneous)
Reference27 articles.
1. Jiang, P., Osteen, P., Wigness, M., and Saripalli, S. (2020). RELLIS-3D Dataset: Data, Benchmarks and Analysis. arXiv. 2. Wigness, M., Eum, S., Rogers Iii, J.G., Han, D., and Kwon, H. (2019, January 3–8). A RUGD Dataset for Autonomous Navigation and Visual Perception in Unstructured Outdoor Environments. Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China. 3. Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016). The Cityscapes Dataset for Semantic Urban Scene Understanding. arXiv. 4. Neuhold, G., Ollmann, T., Bulo, S.R., and Kontschieder, P. (2017, January 22–29). The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy. 5. Survey on deep learning with class imbalance;Johnson;J. Big. Data,2019
|
|