Exploiting effects of parts in fine-grained categorization of vehicles

Liang Liao, Ruimin Hu, Jun Xiao, Qi Wang, Jing Xiao, Jun ChenICIP 2015 · OpenReview

Abstract

Fine-grained categorization has become a hot topic in computer vision. Based on the theory that part information is crucial for fine-grained categorization, we proposed a part-based categorization method for vehicles, consisting vehicle parts localization, part-based vehicle representation and classification. There were three contributions we made in this work: 1) we analyzed discriminative powers of parts for fine-grained categorization; 2) we proposed a frame of how to integrate discriminative powers of parts into categorization, and proved that it can achieve better performance than treating every part equally; 3) we provided an annotated dataset with parts for vehicle categorization.
BibTeX
@inproceedings{liao2015exploiting,
  author = {Liang Liao and Ruimin Hu and Jun Xiao and Qi Wang and Jing Xiao and Jun Chen},
  title = {{Exploiting effects of parts in fine-grained categorization of vehicles}},
  booktitle = {ICIP},
  year = {2015},
  url = {https://openreview.net/forum?id=p7XD3GqAdyT},
}

Loading related content...

Figure