A Large-Scale Car Dataset for Fine-Grained Categorization and Verification

TL;DR

This paper introduces a large-scale car dataset designed for fine-grained categorization and verification, providing new benchmarks and preliminary experimental results to advance research in vehicle recognition.

Contribution

The paper presents a comprehensive, annotated car dataset with train/test splits, enabling improved fine-grained vehicle classification and verification research.

Findings

Preliminary experiment results on surveillance data demonstrate the dataset's utility.

The dataset facilitates fine-grained categorization and verification tasks.

Provides detailed annotations and splits for benchmarking.

Abstract

Updated on 24/09/2015: This update provides preliminary experiment results for fine-grained classification on the surveillance data of CompCars. The train/test splits are provided in the updated dataset. See details in Section 6.