A Large-Scale Car Parts (LSCP) Dataset for Lightweight Fine-Grained Detection
This work addresses a gap in automotive AI for car parts detection, providing a dataset that supports diverse scenarios, though it is incremental as it builds on existing detection methods.
The paper tackles the lack of large-scale datasets for car parts detection by introducing the LSCP dataset with 84,162 images covering 12 car part types, and it evaluates this dataset by training lightweight YOLO detectors for fine-grained detection tasks.
Automotive related datasets have previously been used for training autonomous driving systems or vehicle classification tasks. However, there is a lack of datasets in the field of automotive AI for car parts detection, and most available datasets are limited in size and scope, struggling to cover diverse scenarios. To address this gap, this paper presents a large-scale and fine-grained automotive dataset consisting of 84,162 images for detecting 12 different types of car parts. This dataset was collected from natural cameras and online websites which covers various car brands, scenarios, and shooting angles. To alleviate the burden of manual annotation, we propose a novel semi-supervised auto-labeling method that leverages state-of-the-art pre-trained detectors. Moreover, we study the limitations of the Grounding DINO approach for zero-shot labeling. Finally, we evaluate the effectiveness of our proposed dataset through fine-grained car parts detection by training several lightweight YOLO-series detectors.