Next Article in Journal
Needleless Electrospinning of a Chitosan Lactate Aqueous Solution: Influence of Solution Composition and Spinning Parameters
Previous Article in Journal
Minimum MOS Transistor Count Fractional-Order Voltage-Mode and Current-Mode Filters
Open AccessArticle

Incremental and Multi-Task Learning Strategies for Coarse-To-Fine Semantic Segmentation

1
Department of Information Engineering, University of Padova, 35131 Padova, Italy
2
Higher School of Communication of Tunis (SupCom), Ariana 2083, Tunisia
*
Author to whom correspondence should be addressed.
Technologies 2020, 8(1), 1; https://doi.org/10.3390/technologies8010001
Received: 25 October 2019 / Revised: 12 December 2019 / Accepted: 13 December 2019 / Published: 18 December 2019
(This article belongs to the Special Issue Computer Vision and Image Processing Technologies)
The semantic understanding of a scene is a key problem in the computer vision field. In this work, we address the multi-level semantic segmentation task where a deep neural network is first trained to recognize an initial, coarse, set of a few classes. Then, in an incremental-like approach, it is adapted to segment and label new objects’ categories hierarchically derived from subdividing the classes of the initial set. We propose a set of strategies where the output of coarse classifiers is fed to the architectures performing the finer classification. Furthermore, we investigate the possibility to predict the different levels of semantic understanding together, which also helps achieve higher accuracy. Experimental results on the New York University Depth v2 (NYUDv2) dataset show promising insights on the multi-level scene understanding. View Full-Text
Keywords: semantic segmentation; deep learning; hierarchical learning; incremental learning; multi-task learning semantic segmentation; deep learning; hierarchical learning; incremental learning; multi-task learning
Show Figures

Figure 1

MDPI and ACS Style

Mel, M.; Michieli, U.; Zanuttigh, P. Incremental and Multi-Task Learning Strategies for Coarse-To-Fine Semantic Segmentation. Technologies 2020, 8, 1.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop