Localizing Common Objects Using Common Component Activation mAP
Abstract
In this work, we propose an approach to localize common objects from novel object categories in a set of images. We solve this problem using a new common component activation map (CCAM) in which we treat the class-specific activation maps (CAM) as components to discover the com- mon components in the image set. We show that our approach can generalize on novel object categories in our experiments.
Cite
Text
Li et al. "Localizing Common Objects Using Common Component Activation mAP." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.Markdown
[Li et al. "Localizing Common Objects Using Common Component Activation mAP." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/li2019cvprw-localizing/)BibTeX
@inproceedings{li2019cvprw-localizing,
title = {{Localizing Common Objects Using Common Component Activation mAP}},
author = {Li, Weihao and Jafari, Omid Hosseini and Rother, Carsten},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {28-31},
url = {https://mlanthology.org/cvprw/2019/li2019cvprw-localizing/}
}