Convolutional Scale Invariance for Semantic Segmentation (CROSBI ID 644339)
Prilog sa skupa u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Krešo, Ivan ; Čaušević, Denis ; Krapac, Josip ; Šegvić, Siniša
engleski
Convolutional Scale Invariance for Semantic Segmentation
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.
Convolutional networks, semantic segmentation
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
64-75.
2016.
nije evidentirano
objavljeno
978-3-319-45885-4
Podaci o matičnoj publikaciji
Lecture notes in computer science
Rosenhahn, Bodo, Andres, Bjoern
Hannover: Springer
0302-9743
Podaci o skupu
38th German Conference on Pattern Recognition GCPR 2016.
predavanje
12.09.2016-15.09.2016
Hannover, Njemačka