Car-1000: A New Large Scale Fine-Grained Visual Categorization Dataset

2025-03-16

AI Summary

The Stanford-Car dataset suffers from limited class diversity (196 classes), outdated model coverage (pre-2013), and narrow manufacturer representation, hindering its applicability to downstream autonomous driving tasks. Method: We introduce Car-1000, the first large-scale, modern fine-grained vehicle recognition benchmark, comprising 1,000 production car models launched after 2013 from 165 manufacturers, with high-resolution images and multi-view, human-verified annotations. We formally define a fine-grained recognition task aligned with industrial requirements and benchmark state-of-the-art methods—including MA-CNN, PMG, and TransFG—under a unified evaluation protocol. Contribution/Results: Experiments demonstrate that Car-1000 significantly improves model accuracy on novel vehicle models and enhances cross-year generalization. It establishes a critical data foundation and standardized evaluation framework for advancing fine-grained visual categorization (FGVC) in traffic perception and autonomous driving applications.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Mobility, Driving & Flight

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Fine-grained visual categorization (FGVC) is a challenging but significant task in computer vision, which aims to recognize different sub-categories of birds, cars, airplanes, etc. Among them, recognizing models of different cars has significant application value in autonomous driving, traffic surveillance and scene understanding, which has received considerable attention in the past few years. However, Stanford-Car, the most widely used fine-grained dataset for car recognition, only has 196 different categories and only includes vehicle models produced earlier than 2013. Due to the rapid advancements in the automotive industry during recent years, the appearances of various car models have become increasingly intricate and sophisticated. Consequently, the previous Stanford-Car dataset fails to capture this evolving landscape and cannot satisfy the requirements of automotive industry. To address these challenges, in our paper, we introduce Car-1000, a large-scale dataset designed specifically for fine-grained visual categorization of diverse car models. Car-1000 encompasses vehicles from 165 different automakers, spanning a wide range of 1000 distinct car models. Additionally, we have reproduced several state-of-the-art FGVC methods on the Car-1000 dataset, establishing a new benchmark for research in this field. We hope that our work will offer a fresh perspective for future FGVC researchers. Our dataset is available at https://github.com/toggle1995/Car-1000.

Problem

• Addresses limitations of Stanford-Car dataset for car recognition.
• Introduces Car-1000 dataset for fine-grained car model categorization.
• Establishes new benchmark for FGVC research with Car-1000.

Innovation

• Introduces Car-1000 dataset for FGVC
• Includes 1000 distinct car models
• Reproduces state-of-the-art FGVC methods