Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Huang, Kaixu"'
Class activation map (CAM) highlights regions of classes based on classification network, which is widely used in weakly supervised tasks. However, it faces the problem that the class activation regions are usually small and local. Although several e
Externí odkaz:
http://arxiv.org/abs/1909.09839
Existing method generates class activation map (CAM) by a set of fixed classes (i.e., using all the classes), while the discriminative cues between class pairs are not considered. Note that activation maps by considering different class pair are comp
Externí odkaz:
http://arxiv.org/abs/1901.07683
Autor:
Meng, Fanman1 (AUTHOR) fmmeng@uestc.edu.cn, Huang, Kaixu1 (AUTHOR), Li, Hongliang1 (AUTHOR), Chen, Shuai1 (AUTHOR), Wu, Qingbo1 (AUTHOR), Ngan, King N.1 (AUTHOR)
Publikováno v:
Neural Computing & Applications. Jul2021, Vol. 33 Issue 13, p7371-7380. 10p.
Publikováno v:
Neural Computing and Applications. 33:7371-7380
Class activation map (CAM) generation aims at highlighting regions of a class in an image by the classification model. However, the regions obtained are usually small and local. Existing methods attribute the problem to the ineffective CAM extraction
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
DICTA
Class activation map (CAM) highlights regions of classes based on classification network, which is widely used in weakly supervised tasks. However, it faces the problem that the class activation regions are usually small and local. Although several e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c16f7c7f05b9a89dc099dc20af59c8e
http://arxiv.org/abs/1909.09839
http://arxiv.org/abs/1909.09839
Publikováno v:
Chinese Journal of Lasers. 35:137-141