English

Classification-Specific Parts for Improving Fine-Grained Visual Categorization

Computer Vision and Pattern Recognition 2020-07-07 v1 Machine Learning

Abstract

Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance. While global approaches aim at using the whole image for performing the classification, part-based solutions gather additional local information in terms of attentions or parts. We propose a novel classification-specific part estimation that uses an initial prediction as well as back-propagation of feature importance via gradient computations in order to estimate relevant image regions. The subsequently detected parts are then not only selected by a-posteriori classification knowledge, but also have an intrinsic spatial extent that is determined automatically. This is in contrast to most part-based approaches and even to available ground-truth part annotations, which only provide point coordinates and no additional scale information. We show in our experiments on various widely-used fine-grained datasets the effectiveness of the mentioned part selection method in conjunction with the extracted part features.

Keywords

Cite

@article{arxiv.1909.07075,
  title  = {Classification-Specific Parts for Improving Fine-Grained Visual Categorization},
  author = {Dimitri Korsch and Paul Bodesheim and Joachim Denzler},
  journal= {arXiv preprint arXiv:1909.07075},
  year   = {2020}
}

Comments

Presented at the GCPR2019

R2 v1 2026-06-23T11:16:25.018Z