Weakly-Supervised Semantic Segmentation by Redistributing Region Scores Back to the Pixels (CROSBI ID 644340)
Prilog sa skupa u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Krapac, Josip ; Šegvić, Siniša
engleski
Weakly-Supervised Semantic Segmentation by Redistributing Region Scores Back to the Pixels
We address the problem of semantic segmentation of objects in weakly supervised setting, when only image-wide labels are available. We describe an image with a set of pre-trained convolutional features and embed this set into a Fisher vector. We apply the learned image classifier on the set of all image regions and propagate the region scores back to the pixels. Compared to the alternatives the proposed method is simple, fast in inference, and especially in training. The method displays very good performance of on two standard semantic segmentation benchmarks.
Convolutional networks, weakly supervised localization
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
377-388.
2016.
nije evidentirano
objavljeno
Podaci o matičnoj publikaciji
Rosenhahn, Bodo, Andres, Bjoern
Hannover: Springer
978-3-319-45885-4
0302-9743
Podaci o skupu
38th German Conference on Pattern Recognition GCPR 2016.
poster
12.09.2016-15.09.2016
Hannover, Njemačka