@inproceedings{korsch2019classificationspecific,
    type = {inproceedings},
    key = {korsch2019classificationspecific},
    title = {Classification-Specific Parts for Improving Fine-Grained Visual Categorization},
    author = {Dimitri Korsch and Paul Bodesheim and Joachim Denzler},
    booktitle = {DAGM German Conference on Pattern Recognition (DAGM-GCPR)},
    year = {2019},
    editor = {Gernot A. Fink and Simone Frintrop and Xiaoyi Jiang},
    pages = {62-75},
    publisher = {Springer International Publishing},
    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.},
    code = {https://github.com/DiKorsch/l1_parts},
    doi = {10.1007/978-3-030-33676-9_5},
    groups = {finegrained,featurelearning},
    isbn = {978-3-030-33676-9},
    url = {https://doi.org/10.1007/978-3-030-33676-9_5},
}