期刊
IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT II
卷 11752, 期 -, 页码 303-314出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-30645-8_28
关键词
Deep Convolutional Neural Networks; Semantic segmentation; Scene understanding
类别
资金
- TEINVEIN - Call Accordi per la Ricerca e l'Innovazione [CUP: E96D1700011 0009]
- POR FESR 2014-2020
- NVIDIA Corporation
In the past few years, various datasets for semantic segmentation have been presented. However, dense per-pixel groundtruths are difficult and expensive to obtain, therefore every single dataset contains only a subset of the semantic classes required to fully understand outdoor environments for real-world applications, e.g. autonomous or assisted driving. In this work, we investigate a simple approach to modify semantic segmentation CNNs in order to train them on multiple datasets with heterogeneous groundtruths. We trained and tested six efficient Deep CNN models on three datasets with different types of annotations such as generic objects, traffic signs and lane markings. Experiments show that the networks are trainable with the implemented method even though it highlights the limit of current efficient architectures when dealing with heterogeneous and large datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据