{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-systematic-evaluation-of-recent-deep","title":"A Systematic Evaluation of Recent Deep Learning Architectures for Fine-Grained Vehicle Classification","arxiv_id":"1806.02987","date":"2018-06-08","proceeding":null,"authors":["Krassimir Valev","Arne Schumann","Lars Sommer","Jürgen Beyerer"],"abstract":"Fine-grained vehicle classification is the task of classifying make, model,\nand year of a vehicle. This is a very challenging task, because vehicles of\ndifferent types but similar color and viewpoint can often look much more\nsimilar than vehicles of same type but differing color and viewpoint. Vehicle\nmake, model, and year in com- bination with vehicle color - are of importance\nin several applications such as vehicle search, re-identification, tracking,\nand traffic analysis. In this work we investigate the suitability of several\nrecent landmark convolutional neural network (CNN) architectures, which have\nshown top results on large scale image classification tasks, for the task of\nfine-grained classification of vehicles. We compare the performance of the\nnetworks VGG16, several ResNets, Inception architectures, the recent DenseNets,\nand MobileNet. For classification we use the Stanford Cars-196 dataset which\nfeatures 196 different types of vehicles. We investigate several aspects of CNN\ntraining, such as data augmentation and training from scratch vs. fine-tuning.\nImportantly, we introduce no aspects in the architectures or training process\nwhich are specific to vehicle classification. Our final model achieves a\nstate-of-the-art classification accuracy of 94.6% outperforming all related\nworks, even approaches which are specifically tailored for the task, e.g. by\nincluding vehicle part detections.","url_abs":"http://arxiv.org/abs/1806.02987v1","url_pdf":"http://arxiv.org/pdf/1806.02987v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-systematic-evaluation-of-recent-deep","repo_url":"https://github.com/OrkhanHI/Grab-AI-Computer-Vision-Challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"fine-grained-vehicle-classification","task_name":"Fine-Grained Vehicle Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}