{"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/densenet-implementing-efficient-convnet","title":"DenseNet: Implementing Efficient ConvNet Descriptor Pyramids","arxiv_id":"1404.1869","date":"2014-04-07","proceeding":null,"authors":["Forrest Iandola","Matt Moskewicz","Sergey Karayev","Ross Girshick","Trevor Darrell","Kurt Keutzer"],"abstract":"Convolutional Neural Networks (CNNs) can provide accurate object\nclassification. They can be extended to perform object detection by iterating\nover dense or selected proposed object regions. However, the runtime of such\ndetectors scales as the total number and/or area of regions to examine per\nimage, and training such detectors may be prohibitively slow. However, for some\nCNN classifier topologies, it is possible to share significant work among\noverlapping regions to be classified. This paper presents DenseNet, an open\nsource system that computes dense, multiscale features from the convolutional\nlayers of a CNN based object classifier. Future work will involve training\nefficient object detectors with DenseNet feature descriptors.","url_abs":"http://arxiv.org/abs/1404.1869v1","url_pdf":"http://arxiv.org/pdf/1404.1869v1.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":"densenet-implementing-efficient-convnet","repo_url":"https://github.com/forresti/caffe","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"densenet-implementing-efficient-convnet","repo_url":"https://github.com/2023-MindSpore-4/Code8/tree/main/3D_DenseNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"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=1404.1869","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}