{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T18:05:50Z","timestamp":1789236350188,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375490","type":"print"},{"value":"9783032375506","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37550-6_28","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:21:35Z","timestamp":1789233695000},"page":"485-501","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Head Normalization for\u00a0Wide Vision Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4512-4537","authenticated-orcid":false,"given":"Guoyizhe","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7553-3184","authenticated-orcid":false,"given":"Feng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5207-9249","authenticated-orcid":false,"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7638-1650","authenticated-orcid":false,"given":"Rama","family":"Chellappa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"28_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization (2016)"},{"key":"28_CR2","unstructured":"Bachlechner, T., Majumder, B.P., Mao, H.H., Cottrell, G., McAuley, J.: Rezero is all you need: fast convergence at large depth. In: ICLR (2021)"},{"key":"28_CR3","unstructured":"Bai, J., et al.: Qwen technical report (2023)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers, p. ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Zhang, Z., Cheng, Y., Awadallah, A., Wang, Z.: The principle of diversity: training stronger vision transformers calls for reducing all levels of redundancy. CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01171"},{"key":"28_CR6","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. ICLR (2024)"},{"key":"28_CR7","unstructured":"Ding, M., Yang, Z., Hong, W.: CogView: mastering text-to-image generation via transformers. NeurIPS (2021)"},{"key":"28_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale, p. ICLR (2021)"},{"key":"28_CR9","unstructured":"Graef, N., Clapp, M., Wasielewski, A.: Flash normalization: fast RMSnorm for LLMs (2024)"},{"key":"28_CR10","unstructured":"Grattafiori, A., et al.: The Llama 3 herd of models (2024)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Henry, A., Dachapally, P.R., Pawar, S., Chen, Y., Mueller, J., Koyejo, S.: Query-Key normalization for transformers. EMNLP (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.379"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer V2: scaling up capacity and resolution. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"28_CR16","unstructured":"Mohan, N.V., et al.: Gated removal of normalization in transformers enables stable training and efficient inference (2026)"},{"key":"28_CR17","unstructured":"Nguyen, T.Q., Salazar, J.: Transformers without tears: improving the normalization of self-attention. IWSLT (2019)"},{"key":"28_CR18","unstructured":"Oquab, M., et al.: DINOv2: Learning robust visual features without supervision. TMLR (2024)"},{"key":"28_CR19","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., et\u00a0al.: DINOv3 (2025)"},{"key":"28_CR20","unstructured":"Qi, X., Wang, J., Chen, Y., Shi, Y., Zhang, L.: LipsFormer: introducing lipschitz continuity to vision transformers, p. ICLR (2023)"},{"key":"28_CR21","unstructured":"Qwen, et al.: Qwen2.5 technical report (2024)"},{"key":"28_CR22","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR (2020)"},{"key":"28_CR23","unstructured":"Shen, S., Yao, Z., Gholami, A., Mahoney, M., Keutzer, K.: PowerNorm: rethinking batch normalization in transformers, p. ICML (2020)"},{"key":"28_CR24","unstructured":"Shleifer, S., Weston, J., Ott, M.: NormFormer: improved transformer pretraining with extra normalization. ICLR (2022)"},{"key":"28_CR25","unstructured":"Sun, M., Chen, X., Kolter, J.Z., Liu, Z.: Massive activations in large language models. COLM (2024)"},{"key":"28_CR26","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Deit iii: Revenge of the vit. ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers, p. ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"28_CR29","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023)"},{"key":"28_CR30","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023)"},{"key":"28_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. NeurIPS (2017)"},{"key":"28_CR32","unstructured":"Wang, F., et al.: ViT-5: Vision transformers for the mid-2020s (2026)"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Ma, S., Dong, L., Wei, F., Liu, T.Y.: DeepNet: scaling transformers to 1,000 layers, PAMI (2024)","DOI":"10.1109\/TPAMI.2024.3386927"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization, p. ECCV (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding ECCV (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"28_CR36","unstructured":"Xiong, R., et al.: On layer normalization in the transformer architecture. ICML (2020)"},{"key":"28_CR37","unstructured":"Yang, A., et al.: Qwen3 technical report (2025)"},{"key":"28_CR38","unstructured":"Yang, A., et\u00a0al.: Qwen2 technical report (2024)"},{"key":"28_CR39","unstructured":"You, Y., et al.: Large batch optimization for deep learning: training BERT in 76 minutes, p. ICLR (2020)"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training, p. ICML (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"28_CR41","unstructured":"Zhang, B., Sennrich, R.: Root mean square layer normalization (2019)"},{"key":"28_CR42","unstructured":"Zhang, H., Dauphin, Y.N., Ma, T.: Fixup initialization: Residual learning without normalization, p. ICLR (2019)"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Semantic understanding of scenes through the ade20k dataset. IJCV (2019)","DOI":"10.1007\/s11263-018-1140-0"},{"key":"28_CR44","unstructured":"Zhou, D., et al.: DeepViT: Towards deeper vision transformer (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37550-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:21:48Z","timestamp":1789233708000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37550-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375490","9783032375506"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37550-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}