Fine-Grained Visual Classification of Aircraft

TL;DR

This paper introduces FGVC-Aircraft, a detailed dataset for aircraft classification, along with benchmarks, highlighting the challenges and unique variations in aircraft visual recognition.

Contribution

The creation of a comprehensive aircraft dataset with hierarchical classification tasks and baseline results for fine-grained visual recognition.

Findings

Dataset contains 10,000 images of 100 aircraft models.

Aircraft exhibit unique variations like purpose, size, and style.

Baseline classification results are provided.

Abstract

This paper introduces FGVC-Aircraft, a new dataset containing 10,000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy. At the finer level, differences between models are often subtle but always visually measurable, making visual recognition challenging but possible. A benchmark is obtained by defining corresponding classification tasks and evaluation protocols, and baseline results are presented. The construction of this dataset was made possible by the work of aircraft enthusiasts, a strategy that can extend to the study of number of other object classes. Compared to the domains usually considered in fine-grained visual classification (FGVC), for example animals, aircraft are rigid and hence less deformable. They, however, present other interesting modes of variation, including purpose, size, designation, structure, historical style, and branding.