{"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/cross-dataset-training-for-class-increasing","title":"Cross-dataset Training for Class Increasing Object Detection","arxiv_id":"2001.04621","date":"2020-01-14","proceeding":null,"authors":["Yongqiang Yao","Yan Wang","Yu Guo","Jiaojiao Lin","Hongwei Qin","Junjie Yan"],"abstract":"We present a conceptually simple, flexible and general framework for cross-dataset training in object detection. Given two or more already labeled datasets that target for different object classes, cross-dataset training aims to detect the union of the different classes, so that we do not have to label all the classes for all the datasets. By cross-dataset training, existing datasets can be utilized to detect the merged object classes with a single model. Further more, in industrial applications, the object classes usually increase on demand. So when adding new classes, it is quite time-consuming if we label the new classes on all the existing datasets. While using cross-dataset training, we only need to label the new classes on the new dataset. We experiment on PASCAL VOC, COCO, WIDER FACE and WIDER Pedestrian with both solo and cross-dataset settings. Results show that our cross-dataset pipeline can achieve similar impressive performance simultaneously on these datasets compared with training independently.","url_abs":"https://arxiv.org/abs/2001.04621v1","url_pdf":"https://arxiv.org/pdf/2001.04621v1.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":"cross-dataset-training-for-class-increasing","repo_url":"https://github.com/yqyao/cross_focal_loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cross-dataset-training-for-class-increasing","repo_url":"https://github.com/MindCode-4/code-11/tree/main/corss-dataset-training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"cross-dataset-training-for-class-increasing","repo_url":"https://github.com/MindCode-4/code-6/tree/main/corss-dataset-training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"cross-dataset-training-for-class-increasing","repo_url":"https://github.com/MindSpore-scientific/code-3/tree/main/corss-dataset-training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.04621","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}