Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization

• Published in: arXiv.org
• Main Authors: Lv, Pei, Yu, Haiyu, Xue, Junxiao, Cheng, Junjin, Cui, Lisha, Zhou, Bing, Xu, Mingliang, Yang, Yi
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 24.09.2019
• Subjects: Activation; Artificial neural networks; Computer vision; Datasets; Feature maps; Localization; Multiscale analysis

Localizing objects with weak supervision in an image is a key problem of the research in computer vision community. Many existing Weakly-Supervised Object Localization (WSOL) approaches tackle this problem by estimating the most discriminative regions with feature maps (activation maps) obtained by...