There are a total of 136,726 images capturing the entire cars and 27,618 images capturing the car parts. The web-nature data contains 163 car makes with 1,716 car models. The Comprehensive Cars (CompCars) dataset contains data from two scenarios, including images from web-nature and surveillance-nature. A Large-Scale Car Dataset for Fine-Grained Categorization and Verification, In Computer Vision and Pattern Recognition (CVPR), 2015. Linjie Yang, Ping Luo, Chen Change Loy, Xiaoou Tang. This dataset is presented in our CVPR 2015 paper, First release of CompCars, surveillance-nature images are still under organization and will be released shortly. The fine-tuned GoogLeNet model is uploaded to the Caffe Model Zoo. Train/test splits can be downloaded here. As an extension to our CVPR paper, we conduct experiments for fine-grained car classification, attribute prediction, and car verification with the entire dataset and different deep models. The results are provided in the arXiv paper. We also conducted a fine-grained classification experiment for this part of data. Download all such files, then unzip them with the same password as the web-nature data. Surveillance-nature images are released in the download links as "sv_data.*". CompCars Dataset The Comprehensive Cars (CompCars) dataset
0 Comments
Leave a Reply. |