{"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/scalable-object-detection-using-deep-neural","title":"Scalable Object Detection using Deep Neural Networks","arxiv_id":"1312.2249","date":"2013-12-08","proceeding":"CVPR 2014 6","authors":["Dumitru Erhan","Christian Szegedy","Alexander Toshev","Dragomir Anguelov"],"abstract":"Deep convolutional neural networks have recently achieved state-of-the-art\nperformance on a number of image recognition benchmarks, including the ImageNet\nLarge-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on\nthe localization sub-task was a network that predicts a single bounding box and\na confidence score for each object category in the image. Such a model captures\nthe whole-image context around the objects but cannot handle multiple instances\nof the same object in the image without naively replicating the number of\noutputs for each instance. In this work, we propose a saliency-inspired neural\nnetwork model for detection, which predicts a set of class-agnostic bounding\nboxes along with a single score for each box, corresponding to its likelihood\nof containing any object of interest. The model naturally handles a variable\nnumber of instances for each class and allows for cross-class generalization at\nthe highest levels of the network. We are able to obtain competitive\nrecognition performance on VOC2007 and ILSVRC2012, while using only the top few\npredicted locations in each image and a small number of neural network\nevaluations.","url_abs":"http://arxiv.org/abs/1312.2249v1","url_pdf":"http://arxiv.org/pdf/1312.2249v1.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":"scalable-object-detection-using-deep-neural","repo_url":"https://github.com/Adren98/EczemaApp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"scalable-object-detection-using-deep-neural","repo_url":"https://github.com/GenesisDCarmen/C_Reconocimiento_Facial","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"scalable-object-detection-using-deep-neural","repo_url":"https://github.com/Xephyrum/Agriculturice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"scalable-object-detection-using-deep-neural","repo_url":"https://github.com/Xephyrum/CropsMD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"scalable-object-detection-using-deep-neural","repo_url":"https://github.com/leoliao2008/TensorflowMobileOfficialExample","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"scalable-object-detection-using-deep-neural","repo_url":"https://github.com/sgrvinod/a-pytorch-tutorial-to-object-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1312.2249","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}