ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding

Harald Hanselmann, Hermann Ney; The IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 1247-1256

Abstract


The task of fine-grained visual classification (FGVC) deals with classification problems that display a small inter-class variance such as distinguishing between different bird species or car models. State-of-the-art approaches typically tackle this problem by integrating an elaborate attention mechanism or (part-) localization method into a standard convolutional neural network (CNN). Also in this work the aim is to enhance the performance of a backbone CNN such as ResNet by including three efficient and lightweight components specifically designed for FGVC. This is achieved by using global k-max pooling, a discriminative embedding layer trained by optimizing class means and an efficient localization module that estimates bounding boxes using only class labels for training. The resulting model achieves state-of-the-art recognition accuracies on multiple FGVC benchmark datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Hanselmann_2020_WACV,
author = {Hanselmann, Harald and Ney, Hermann},
title = {ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}