Performance Assessment of Convolutional Neural Networks for Semantic Image Segmentation
| dc.contributor.author | Leipnitz, Alexander | |
| dc.contributor.author | Strutz, Tilo | |
| dc.contributor.author | Jokisch, Oliver | |
| dc.contributor.editor | Skala, Václav | |
| dc.date.accessioned | 2019-10-22T09:09:06Z | |
| dc.date.available | 2019-10-22T09:09:06Z | |
| dc.date.issued | 2019 | |
| dc.description.abstract-translated | Convolutional neural networks are applied successfully for image classification and object detection. Recently, they have been adopted to semantic segmentation tasks and several new network architectures have been proposed. With respect to automotive applications, the Cityscapes dataset is often used as a benchmark. It is one of the biggest datasets in this field and consists of a training, a validation, and a test set. While training and validation allow the optimisation of these nets, the test dataset can be used to evaluate their performance. Our investigations have shown that while these networks perform well for images of the Cityscapes dataset, their segmentation quality significantly drops when applied to new data. It seems that they have limited generalisation abilities. In order to find out whether the image content itself or other image properties cause this effect, we have carried out systematic investigations with modified Cityscapes data. We have found that camera-dependent image properties like brightness, contrast, or saturation can significantly influence the segmentation quality. This papers presents the results of these tests including eight state-of-the-art CNNs. It can be concluded that the out-of-the-boxusage of CNNs in real-world environments is not recommended. | en |
| dc.format | 9 s. | cs |
| dc.format.mimetype | application/odt | |
| dc.identifier.citation | WSCG 2019: full papers proceedings: 27. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 27-35. | en |
| dc.identifier.doi | https://doi.org/10.24132/CSRN.2019.2901.1.4 | |
| dc.identifier.isbn | 978-80-86943-37-4 (CD/-ROM) | |
| dc.identifier.issn | 2464–4617 (print) | |
| dc.identifier.issn | 2464-4625 (CD/DVD) | |
| dc.identifier.uri | http://hdl.handle.net/11025/35606 | |
| dc.language.iso | en | en |
| dc.publisher | Václav Skala - UNION Agency | cs |
| dc.rights | © Václav Skala - UNION Agency | cs |
| dc.rights.access | openAccess | en |
| dc.subject | konvoluční neuronová síť | cs |
| dc.subject | sémantická segmentace | cs |
| dc.subject | generalizační schopnosti | cs |
| dc.subject.translated | convolutional neural network | en |
| dc.subject.translated | semantic segmentation | en |
| dc.subject.translated | generalisation abilities | en |
| dc.title | Performance Assessment of Convolutional Neural Networks for Semantic Image Segmentation | en |
| dc.type | konferenční příspěvek | cs |
| dc.type | conferenceObject | en |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |
Files
Original bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- Leipnitz.pdf
- Size:
- 845.78 KB
- Format:
- Adobe Portable Document Format
- Description:
- Plný text
License bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: