{"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/spatial-pyramid-pooling-in-deep-convolutional","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","arxiv_id":"1406.4729","date":"2014-06-18","proceeding":null,"authors":["Kaiming He","Xiangyu Zhang","Shaoqing Ren","Jian Sun"],"abstract":"Existing deep convolutional neural networks (CNNs) require a fixed-size\n(e.g., 224x224) input image. This requirement is \"artificial\" and may reduce\nthe recognition accuracy for the images or sub-images of an arbitrary\nsize/scale. In this work, we equip the networks with another pooling strategy,\n\"spatial pyramid pooling\", to eliminate the above requirement. The new network\nstructure, called SPP-net, can generate a fixed-length representation\nregardless of image size/scale. Pyramid pooling is also robust to object\ndeformations. With these advantages, SPP-net should in general improve all\nCNN-based image classification methods. On the ImageNet 2012 dataset, we\ndemonstrate that SPP-net boosts the accuracy of a variety of CNN architectures\ndespite their different designs. On the Pascal VOC 2007 and Caltech101\ndatasets, SPP-net achieves state-of-the-art classification results using a\nsingle full-image representation and no fine-tuning.\n  The power of SPP-net is also significant in object detection. Using SPP-net,\nwe compute the feature maps from the entire image only once, and then pool\nfeatures in arbitrary regions (sub-images) to generate fixed-length\nrepresentations for training the detectors. This method avoids repeatedly\ncomputing the convolutional features. In processing test images, our method is\n24-102x faster than the R-CNN method, while achieving better or comparable\naccuracy on Pascal VOC 2007.\n  In ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2014, our\nmethods rank #2 in object detection and #3 in image classification among all 38\nteams. This manuscript also introduces the improvement made for this\ncompetition.","url_abs":"http://arxiv.org/abs/1406.4729v4","url_pdf":"http://arxiv.org/pdf/1406.4729v4.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":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/Bribak/DeepConnection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/alegonz/kdsb17","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/daveboat/spp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/rajkumargithub/densenet.mura","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/szagoruyko/imagine-nn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/tdhock/feature-learning-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/xiamenwcy/extended-caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/yhenon/keras-spp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/yueruchen/sppnet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/zhanghuiyao/yolov5_mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/Mind23-2/MindCode-88/tree/main/SPPNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/addisonklinke/pytorch-architectures/blob/master/torcharch/conv.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/mindspore-ai/models/blob/master/research/cv/SPPNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"spatial-pyramid-pooling-in-deep-convolutional","repo_url":"https://github.com/yangyucheng000/ms_cv/tree/main/SPPNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"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"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"local-contrast-normalization","method_name":"Local Contrast Normalization"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"overfeat","method_name":"OverFeat"},{"method_slug":"r-cnn","method_name":"R-CNN"},{"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","method_name":"SGD"},{"method_slug":"spp-net","method_name":"SPP-Net"},{"method_slug":"svm","method_name":"SVM"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"zfnet","method_name":"ZFNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"spp-net","name":"SPP-Net","full_name":"SPP-Net"},{"slug":"spatial-pyramid-pooling","name":"Spatial Pyramid Pooling","full_name":"Spatial Pyramid Pooling"}],"results":[{"leaderboard":"/sota/object-detection-on-pascal-voc-2007","task":"Object Detection","dataset":"PASCAL VOC 2007","model":"SPP(combination)","rank_in_archive_order":25,"of":30,"metrics":{"MAP":"60.9%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1406.4729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1406.4729"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-88/tree/main/SPPNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yhenon/keras-spp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Bribak/DeepConnection","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/addisonklinke/pytorch-architectures/blob/master/torcharch/conv.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yueruchen/sppnet-pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daveboat/spp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tdhock/feature-learning-benchmark","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhanghuiyao/yolov5_mindspore","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/szagoruyko/imagine-nn","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiamenwcy/extended-caffe","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alegonz/kdsb17","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/blob/master/research/cv/SPPNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/ms_cv/tree/main/SPPNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rajkumargithub/densenet.mura","reach":{"status":"unanswered"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"219750c70f6a7cbf","entry":"spatial_pyramid_pool","repo":"yueruchen/sppnet-pytorch","repo_kind":"listed","path":"spp_layer.py","file_url":"https://github.com/yueruchen/sppnet-pytorch/blob/HEAD/spp_layer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"219750c70f6a7cbf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}