{"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/estimated-depth-map-helps-image","title":"Estimated Depth Map Helps Image Classification","arxiv_id":"1709.07077","date":"2017-09-20","proceeding":null,"authors":["Yihui He"],"abstract":"We consider image classification with estimated depth. This problem falls\ninto the domain of transfer learning, since we are using a model trained on a\nset of depth images to generate depth maps (additional features) for use in\nanother classification problem using another disjoint set of images. It's\nchallenging as no direct depth information is provided. Though depth estimation\nhas been well studied, none have attempted to aid image classification with\nestimated depth. Therefore, we present a way of transferring domain knowledge\non depth estimation to a separate image classification task over a disjoint set\nof train, and test data. We build a RGBD dataset based on RGB dataset and do\nimage classification on it. Then evaluation the performance of neural networks\non the RGBD dataset compared to the RGB dataset. From our experiments, the\nbenefit is significant with shallow and deep networks. It improves ResNet-20 by\n0.55% and ResNet-56 by 0.53%. Our code and dataset are available publicly.","url_abs":"http://arxiv.org/abs/1709.07077v1","url_pdf":"http://arxiv.org/pdf/1709.07077v1.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":"estimated-depth-map-helps-image","repo_url":"https://github.com/yihui-he/Estimated-Depth-Map-Helps-Image-Classification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}