LayerCAM: Exploring Hierarchical Class Activation Maps for Localization

The class activation maps are generated from the final convolutional layer of CNN. They can highlight discriminative object regions for the class of interest. These discovered object regions have been widely used for weakly-supervised tasks. However, due to the small spatial resolution of the final...

Celý popis

Podrobná bibliografie

Vydáno v:	IEEE transactions on image processing Ročník 30; s. 5875 - 5888
Hlavní autoři:	Jiang, Peng-Tao, Zhang, Chang-Bin, Hou, Qibin, Cheng, Ming-Ming, Wei, Yunchao
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	class activation maps Convolution Feature maps Image segmentation Localization Location awareness Pixels Reliability Semantic segmentation Semantics Spatial resolution Task analysis Weakly-supervised object localization
ISSN:	1057-7149, 1941-0042, 1941-0042
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!