Fine-grained Recognition Datasets for Biodiversity Analysis

TL;DR

This paper introduces two challenging fine-grained visual classification datasets for biodiversity analysis, demonstrating initial CNN-based results and outlining future research directions in the field.

Contribution

It provides new biodiversity datasets with many similar classes and explores CNN-based localized features for fine-grained recognition.

Findings

Initial CNN results on the datasets show promising accuracy.

The datasets pose significant challenges for current visual classification methods.

The paper highlights future research directions in biodiversity visual recognition.

Abstract

In the following paper, we present and discuss challenging applications for fine-grained visual classification (FGVC): biodiversity and species analysis. We not only give details about two challenging new datasets suitable for computer vision research with up to 675 highly similar classes, but also present first results with localized features using convolutional neural networks (CNN). We conclude with a list of challenging new research directions in the area of visual classification for biodiversity research.