Naslov
Convolutional Scale Invariance for Semantic Segmentation

Autori
Krešo, Ivan ; Čaušević, Denis ; Krapac, Josip ; Šegvić, Siniša

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

Izvornik
Pattern Recognition. 38th German Conference, GCPR 2016, Hannover, Germany, September 12-15, 2016, Proceedings. Lecture Notes in Computer Science, Vol. 9796. / Rosenhahn, Bodo, Andres, Bjoern - Hannover : Springer, 2016, 64-75

ISBN
978-3-319-45885-4

Skup
38th German Conference on Pattern Recognition GCPR 2016.

Mjesto i datum
Hannover, Njemačka, 12.09.2016. - 15.09.2016

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Convolutional networks, semantic segmentation

Sažetak
We propose an effective technique to address large scale variation in images taken from a moving car by cross-breeding deep learning with stereo reconstruction. Our main contribution is a novel scale selection layer which extracts convolutional features at the scale which matches the corresponding reconstructed depth. The recovered scale-invariant representation disentangles appearance from scale and frees the pixel-level classifier from the need to learn the laws of the perspective. This results in improved segmentation results due to more efficient exploitation of representation capacity and training data. We perform experiments on two challenging stereoscopic datasets (KITTI and Cityscapes) and report competitive class-level IoU performance.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA