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

TL;DR

This paper introduces ELoPE, a lightweight model for fine-grained visual classification that enhances CNNs with efficient localization, pooling, and embedding components, achieving state-of-the-art results.

Contribution

It proposes three novel lightweight components—global k-max pooling, a discriminative embedding layer, and a bounding box estimator—for improved FGVC performance.

Findings

Achieves new state-of-the-art accuracy on Stanford cars dataset.

Outperforms existing methods on FGVC-Aircraft dataset.

Uses only class labels for bounding box estimation.

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 bounding box estimator that only needs class labels for training. The resulting model achieves new best state-of-the-art recognition accuracies on the Stanford cars and FGVC-Aircraft datasets.