{"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/megdet-a-large-mini-batch-object-detector","title":"MegDet: A Large Mini-Batch Object Detector","arxiv_id":"1711.07240","date":"2017-11-20","proceeding":"CVPR 2018 6","authors":["Chao Peng","Tete Xiao","Zeming Li","Yuning Jiang","Xiangyu Zhang","Kai Jia","Gang Yu","Jian Sun"],"abstract":"The improvements in recent CNN-based object detection works, from R-CNN [11],\nFast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly\ncome from new network, new framework, or novel loss design. But mini-batch\nsize, a key factor in the training, has not been well studied. In this paper,\nwe propose a Large MiniBatch Object Detector (MegDet) to enable the training\nwith much larger mini-batch size than before (e.g. from 16 to 256), so that we\ncan effectively utilize multiple GPUs (up to 128 in our experiments) to\nsignificantly shorten the training time. Technically, we suggest a learning\nrate policy and Cross-GPU Batch Normalization, which together allow us to\nsuccessfully train a large mini-batch detector in much less time (e.g., from 33\nhours to 4 hours), and achieve even better accuracy. The MegDet is the backbone\nof our submission (mmAP 52.5%) to COCO 2017 Challenge, where we won the 1st\nplace of Detection task.","url_abs":"http://arxiv.org/abs/1711.07240v4","url_pdf":"http://arxiv.org/pdf/1711.07240v4.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":"megdet-a-large-mini-batch-object-detector","repo_url":"https://github.com/CSAILVision/semantic-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"megdet-a-large-mini-batch-object-detector","repo_url":"https://github.com/Louis24/Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"megdet-a-large-mini-batch-object-detector","repo_url":"https://github.com/chenyilun95/tf-cpn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"megdet-a-large-mini-batch-object-detector","repo_url":"https://github.com/chrisway613/Synchronized-BatchNormalization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"megdet-a-large-mini-batch-object-detector","repo_url":"https://github.com/keyEpoch/semen_seg-kd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"megdet-a-large-mini-batch-object-detector","repo_url":"https://github.com/vacancy/Synchronized-BatchNorm-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"retinanet","method_name":"RetinaNet"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.07240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07240"}},"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/chenyilun95/tf-cpn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Louis24/Segmentation","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vacancy/Synchronized-BatchNorm-PyTorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chrisway613/Synchronized-BatchNormalization","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CSAILVision/semantic-segmentation-pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keyEpoch/semen_seg-kd","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"listed":{"samples":4,"ran":1,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"34902f82ec8552bf","entry":"handy_var","repo":"vacancy/Synchronized-BatchNorm-PyTorch","repo_kind":"listed","path":"tests/test_sync_batchnorm.py","file_url":"https://github.com/vacancy/Synchronized-BatchNorm-PyTorch/blob/HEAD/tests/test_sync_batchnorm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"34902f82ec8552bf"}},{"code_sha256_prefix":"9cd45e4b4fb9ad28","entry":"convert_model","repo":"vacancy/Synchronized-BatchNorm-PyTorch","repo_kind":"listed","path":"sync_batchnorm/batchnorm.py","file_url":"https://github.com/vacancy/Synchronized-BatchNorm-PyTorch/blob/HEAD/sync_batchnorm/batchnorm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9cd45e4b4fb9ad28"}},{"code_sha256_prefix":"b242a8523848aac6","entry":"convert_model","repo":"chrisway613/Synchronized-BatchNormalization","repo_kind":"listed","path":"func.py","file_url":"https://github.com/chrisway613/Synchronized-BatchNormalization/blob/HEAD/func.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b242a8523848aac6"}},{"code_sha256_prefix":"01032887c64a9e22","entry":"patch_replication_callback","repo":"chrisway613/Synchronized-BatchNormalization","repo_kind":"listed","path":"func.py","file_url":"https://github.com/chrisway613/Synchronized-BatchNormalization/blob/HEAD/func.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"01032887c64a9e22"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}