{"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/overfeat-integrated-recognition-localization","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","arxiv_id":"1312.6229","date":"2013-12-21","proceeding":null,"authors":["Pierre Sermanet","David Eigen","Xiang Zhang","Michael Mathieu","Rob Fergus","Yann Lecun"],"abstract":"We present an integrated framework for using Convolutional Networks for\nclassification, localization and detection. We show how a multiscale and\nsliding window approach can be efficiently implemented within a ConvNet. We\nalso introduce a novel deep learning approach to localization by learning to\npredict object boundaries. Bounding boxes are then accumulated rather than\nsuppressed in order to increase detection confidence. We show that different\ntasks can be learned simultaneously using a single shared network. This\nintegrated framework is the winner of the localization task of the ImageNet\nLarge Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very\ncompetitive results for the detection and classifications tasks. In\npost-competition work, we establish a new state of the art for the detection\ntask. Finally, we release a feature extractor from our best model called\nOverFeat.","url_abs":"http://arxiv.org/abs/1312.6229v4","url_pdf":"http://arxiv.org/pdf/1312.6229v4.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":"overfeat-integrated-recognition-localization","repo_url":"https://github.com/sermanet/OverFeat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"overfeat-integrated-recognition-localization","repo_url":"https://github.com/soumith/convnet-benchmarks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"overfeat-integrated-recognition-localization","repo_url":"https://github.com/soumith/imagenet-multiGPU.torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"overfeat-integrated-recognition-localization","repo_url":"https://github.com/vohoaiviet/OverFeat-DeepNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"overfeat","method_name":"OverFeat"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1312.6229","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}