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

arXiv: https://arxiv.org/abs/1911.07344 · HTML: https://mlsanity.com/paper/1911.07344/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2019.

## Built on by (most cited first, 7 of 7)

- [Fine-Grained Visual Classification using Self Assessment Classifier](https://mlsanity.com/paper/2205.10529/) (2022)
- [Enhancing Fine-Grained Classification for Low Resolution Images](https://mlsanity.com/paper/2105.00241/) (2021)
- [ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator](https://mlsanity.com/paper/2203.12816/) (2022)
- [`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2404.08761/) (2024)
- [Learning Granularity-Aware Convolutional Neural Network for Fine-Grained Visual Classification](https://mlsanity.com/paper/2103.02788/) (2021)
- [Semantic Feature Integration network for Fine-grained Visual Classification](https://mlsanity.com/paper/2302.10275/) (2023)
- [EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task](https://mlsanity.com/paper/2509.21061/) (2025)

## Abstract (arXiv)

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.