{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/weight-standardization","title":"Micro-Batch Training with Batch-Channel Normalization and Weight Standardization","arxiv_id":"1903.10520","date":"2019-03-25","proceeding":null,"authors":["Siyuan Qiao","Huiyu Wang","Chenxi Liu","Wei Shen","Alan Yuille"],"abstract":"Batch Normalization (BN) has become an out-of-box technique to improve deep network training. However, its effectiveness is limited for micro-batch training, i.e., each GPU typically has only 1-2 images for training, which is inevitable for many computer vision tasks, e.g., object detection and semantic segmentation, constrained by memory consumption. To address this issue, we propose Weight Standardization (WS) and Batch-Channel Normalization (BCN) to bring two success factors of BN into micro-batch training: 1) the smoothing effects on the loss landscape and 2) the ability to avoid harmful elimination singularities along the training trajectory. WS standardizes the weights in convolutional layers to smooth the loss landscape by reducing the Lipschitz constants of the loss and the gradients; BCN combines batch and channel normalizations and leverages estimated statistics of the activations in convolutional layers to keep networks away from elimination singularities. We validate WS and BCN on comprehensive computer vision tasks, including image classification, object detection, instance segmentation, video recognition and semantic segmentation. All experimental results consistently show that WS and BCN improve micro-batch training significantly. Moreover, using WS and BCN with micro-batch training is even able to match or outperform the performances of BN with large-batch training.","url_abs":"https://arxiv.org/abs/1903.10520v2","url_pdf":"https://arxiv.org/pdf/1903.10520v2.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":"weight-standardization","repo_url":"https://github.com/joe-siyuan-qiao/WeightStandardization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"weight-standardization","repo_url":"https://github.com/ThomasEhling/Weight_Standardization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"weight-standardization","repo_url":"https://github.com/delta6189/Anime-Sketch-Colorizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"weight-standardization","repo_url":"https://github.com/jinfagang/nb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"weight-standardization","repo_url":"https://github.com/lessw2020/auto-adaptive-ai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"weight-standardization","repo_url":"https://github.com/seujung/WeightStandardization_gluon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok"}},{"paper_slug":"weight-standardization","repo_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-recognition","task_name":"Video 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":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnext","method_name":"ResNeXt"},{"method_slug":"resnext-block","method_name":"ResNeXt Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"weight-standardization","method_name":"Weight Standardization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"weight-standardization","name":"Weight Standardization","full_name":"Weight Standardization"}],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Mask R-CNN-FPN (ResNeXt-101, GN+WS)","rank_in_archive_order":79,"of":93,"metrics":{"AP50":"61.07","AP75":"40.82","APL":"56.08","APM":"41.73","APS":"18.32","mask AP":"38.34"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Mask R-CNN-FPN (ResNeXt-101, GN+WS)","rank_in_archive_order":144,"of":220,"metrics":{"AP50":"64.15","AP75":"47.11","APL":"56.39","APM":"47.19","APS":"25.49","box AP":"43.12"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.10520","atlas_url":"https://app.syntology.ai/?focus=1903.10520","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1903.10520"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1903.10520\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1903.10520"},"call":"get_concepts_for_paper(arxiv_id=\"1903.10520\")"}],"by_repo":[{"repo":"joe-siyuan-qiao/WeightStandardization","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ThomasEhling/Weight_Standardization","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"delta6189/Anime-Sketch-Colorizer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.04948"],"harvested_for_calls":[{"arxiv_id":"1812.04948","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.04948"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.04948\")"}]},{"repo":"jinfagang/nb","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lessw2020/auto-adaptive-ai","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seujung/WeightStandardization_gluon","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"labmlai/annotated_deep_learning_paper_implementations","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":15,"harvested_for":["1312.5602","1412.6980","1502.03167","1505.04597","1511.05952","1511.06434","1710.10903","1803.08494","1904.09751","2104.09864","2105.14491","2106.09685","2112.04426","2112.10752","2305.14342"],"harvested_for_calls":[{"arxiv_id":"1312.5602","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1312.5602"},"call":"get_harvested_code_for_paper(arxiv_id=\"1312.5602\")"},{"arxiv_id":"1412.6980","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1412.6980"},"call":"get_harvested_code_for_paper(arxiv_id=\"1412.6980\")"},{"arxiv_id":"1502.03167","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1502.03167"},"call":"get_harvested_code_for_paper(arxiv_id=\"1502.03167\")"},{"arxiv_id":"1505.04597","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1505.04597"},"call":"get_harvested_code_for_paper(arxiv_id=\"1505.04597\")"},{"arxiv_id":"1511.05952","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.05952"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.05952\")"},{"arxiv_id":"1511.06434","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.06434"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.06434\")"},{"arxiv_id":"1710.10903","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10903"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.10903\")"},{"arxiv_id":"1803.08494","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.08494"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.08494\")"},{"arxiv_id":"1904.09751","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.09751"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.09751\")"},{"arxiv_id":"2104.09864","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.09864"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.09864\")"},{"arxiv_id":"2105.14491","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14491"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14491\")"},{"arxiv_id":"2106.09685","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.09685"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.09685\")"},{"arxiv_id":"2112.04426","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.04426"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.04426\")"},{"arxiv_id":"2112.10752","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.10752"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.10752\")"},{"arxiv_id":"2305.14342","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.14342"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.14342\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a6d3fe67d98b2e4221f10ca8e69b2d344ab78d59d9e8fea7373b6660e01637dd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}