Detecting and Grouping Identical Objects for Region Proposal and Classification

Wim Abbeloos, Sergio Caccamo, Esra Ataer Cansizoglu, Yuichi Taguchi, Chen Feng, Teng-Yok Lee

CVPRW 2017 pp. 501-502

doi:10.1109/CVPRW.2017.76 /cvprw/2017/abbeloos2017cvprw-detecting/

Abstract

Often multiple instances of an object occur in the same scene, for example in a warehouse. Unsupervised multi-instance object discovery algorithms are able to detect and identify such objects. We use such an algorithm to provide object proposals to a convolutional neural network (CNN) based classifier. This results in fewer regions to evaluate, compared to traditional region proposal algorithms. Additionally, it enables using the joint probability of multiple instances of an object, resulting in improved classification accuracy. The proposed technique can also split a single class into multiple sub-classes corresponding to the different object types, enabling hierarchical classification.

PDF CVPRW Semantic Scholar

Cite

Text

Abbeloos et al. "Detecting and Grouping Identical Objects for Region Proposal and Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.76

Markdown

[Abbeloos et al. "Detecting and Grouping Identical Objects for Region Proposal and Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/abbeloos2017cvprw-detecting/) doi:10.1109/CVPRW.2017.76

BibTeX

@inproceedings{abbeloos2017cvprw-detecting,
  title     = {{Detecting and Grouping Identical Objects for Region Proposal and Classification}},
  author    = {Abbeloos, Wim and Caccamo, Sergio and Cansizoglu, Esra Ataer and Taguchi, Yuichi and Feng, Chen and Lee, Teng-Yok},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {501-502},
  doi       = {10.1109/CVPRW.2017.76},
  url       = {https://mlanthology.org/cvprw/2017/abbeloos2017cvprw-detecting/}
}