{"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/fine-grained-vehicle-classification-with","title":"Fine-Grained Vehicle Classification with Unsupervised Parts Co-occurrence Learning","arxiv_id":null,"date":"2019-01-23","proceeding":null,"authors":["Sara Elkerdawy","Nilanjan Ray","Hong Zhang"],"abstract":"Vehicle fine-grained classification is a challenging research problem with little attention in the field. In this paper, we propose a deep network architecture for vehicles fine-grained classification without the need of parts or 3D bounding boxes annotation. Co-occurrence layer (COOC) layer is exploited for unsupervised parts discovery. In addition, a two-step procedure with transfer learning and fine-tuning is utilized. This enables us to better fine-tune models with pre-trained weights on ImageNet in some layers while having random initialization in some others. Our model achieves 86.5% accuracy outperforming the state of the art methods in BoxCars116K by 4%. In addition, we achieve 95.5% and 93.19% on CompCars on both train-test splits, 70-30 and 50-50, outperforming the other methods by 4.5% and 8% respectively.","url_abs":"https://openaccess.thecvf.com/content_eccv_2018_workshops/w24/html/Elkerdawy_Fine-Grained_Vehicle_Classification_with_Unsupervised_Parts_Co-occurrence_Learning_ECCVW_2018_paper.html","url_pdf":"https://openaccess.thecvf.com/content_ECCVW_2018/papers/11132/Elkerdawy_Fine-Grained_Vehicle_Classification_with_Unsupervised_Parts_Co-occurrence_Learning_ECCVW_2018_paper.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"fine-grained-vehicle-classification","task_name":"Fine-Grained Vehicle Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-2","task":"Fine-Grained Image Classification","dataset":"BoxCars116K","model":"ResNet152 + COOC","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"86.57%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-compcars","task":"Fine-Grained Image Classification","dataset":"CompCars","model":"Resnet50 + COOC","rank_in_archive_order":4,"of":7,"metrics":{"Accuracy":"95.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}