Naslov
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift

Autori
Bevandić, Petra ; Krešo, Ivan ; Oršić, Marin ; Šegvić, Siniša

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Lecture Notes on Computer Science, vol. 11824 / Fink, Gernot A. ; Frintrop, Simone ; Jiang, Xiaoyi - Dortmund : Springer, 2019, 33-47

ISBN
978-3-030-12939-2

Skup
41th German Conference on Pattern Recognition (GCPR 2019)

Mjesto i datum
Dortmund, Njemačka, 10.09.2019. - 13.09.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Computer vision, semantic segmentation, outlier detection

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA