Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift (CROSBI ID 680006)
Prilog sa skupa u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Bevandić, Petra ; Krešo, Ivan ; Oršić, Marin ; Šegvić, Siniša
engleski
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift
Recent success on realistic road driving datasets has increased interest in exploring robust performance in real-world applications. One of the major unsolved problems is to identify image content which can not be reliably recognized with a given inference engine. We therefore study approaches to recover a dense outlier map alongside the primary task with a single forward pass, by relying on shared convolutional features. We consider semantic segmentation as the primary task and perform extensive validation on WildDash val (inliers), LSUN val (outliers), and pasted objects from Pascal VOC 2007 (outliers). We achieve the best validation performance by training to discriminate inliers from pasted ImageNet-1k content, even though ImageNet-1k contains many road-driving pixels, and, at least nominally, fails to account for the full diversity of the visual world. The proposed two-head model performs comparably to the C-way multi-class model trained to predict uniform distribution in outliers, while outperforming several other validated approaches. We evaluate our best two models on the WildDash test dataset and set a new state of the art on the WildDash benchmark.
Computer vision, semantic segmentation, outlier detection
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
33-47.
2019.
nije evidentirano
objavljeno
10.1007/978-3-030-33676-9_3
Podaci o matičnoj publikaciji
Lecture notes in computer science
Fink, Gernot A. ; Frintrop, Simone ; Jiang, Xiaoyi
Dortmund: Springer
978-3-030-12939-2
0302-9743
Podaci o skupu
41th German Conference on Pattern Recognition (GCPR 2019)
predavanje
10.09.2019-13.09.2019
Dortmund, Njemačka