{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:07:15Z","timestamp":1789024035329,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372109","type":"print"},{"value":"9783032372116","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\/978-3-032-37211-6_36","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:45:19Z","timestamp":1789022719000},"page":"652-668","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Accurate Zero-Shot Quantization via\u00a0Hierarchical Teacher-Assistant Distillation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5982-7110","authenticated-orcid":false,"given":"Wonjin","family":"Cho","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5600-9351","authenticated-orcid":false,"given":"Jeongin","family":"Yun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8774-6950","authenticated-orcid":false,"given":"U.","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Y.: ZeroQ: a novel zero shot quantization framework. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, Y., Yan, R., Liu, Y., Guan, T., He, Y.: TexQ: zero-shot network quantization with texture feature distribution calibration. In: NeurIPS (2023)","DOI":"10.52202\/075280-0014"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Cho, I., Kang, U.: Pea-KD: parameter-efficient and accurate knowledge distillation on BERT. PLOS ONE 17(2), 1\u201312 (2022)","DOI":"10.1371\/journal.pone.0263592"},{"key":"36_CR4","unstructured":"Choi, K.: Qimera: exploiting generating model for zero-shot quantization. In: NeurIPS (2021)"},{"key":"36_CR5","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned step size quantization. In: ICLR (2020)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M.W., Keutzer, K.: A survey of quantization methods for efficient neural network inference. In: Low-Power Computer Vision, pp. 291\u2013326. Chapman and Hall\/CRC (2022)","DOI":"10.1201\/9781003162810-13"},{"key":"36_CR7","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: ICLR (2016)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR9","unstructured":"Hubara, I.: Quantized neural networks: training neural networks with low precision weights and activations. In: JMLR (2018)"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions (2014)","DOI":"10.5244\/C.28.88"},{"issue":"5","key":"36_CR11","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1007\/s10115-022-01818-x","volume":"65","author":"J Jang","year":"2023","unstructured":"Jang, J., Quan, C., Lee, H.D., Kang, U.: FALCON: lightweight and accurate convolution based on depthwise separable convolution. Knowl. Inf. Syst. 65(5), 2225\u20132249 (2023)","journal-title":"Knowl. Inf. Syst."},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Jeon, H., Park, S., Kim, J.G., Kang, U.: PET: parameter-efficient knowledge distillation on transformer. PLOS ONE 18, 1\u201321 (2023)","DOI":"10.1371\/journal.pone.0288060"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Jeon, Y., Lee, C., Kim, H.Y.: Genie: show me the data for quantization. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01161"},{"key":"36_CR14","doi-asserted-by":"publisher","unstructured":"Jiang, Y., Feng, C., Zhang, F., Bull, D.: MTKD: multi-teacher knowledge distillation for image super-resolution. In: ECCV. Springer, Switzerland (2024). https:\/\/doi.org\/10.1007\/978-3-031-72933-1_21","DOI":"10.1007\/978-3-031-72933-1_21"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Kim, J., Jung, J., Kang, U.: Compressing deep graph convolution network with multi-staged knowledge distillation. PLOS ONE 16, 1\u201318 (2021)","DOI":"10.1371\/journal.pone.0256187"},{"key":"36_CR16","unstructured":"Kim, M., Choi, J., Yang, H., Kim, J., Song, J., Kang, U.: Prune-then-quantize or quantize-then-prune? Understanding the impact of compression order in joint model compression. In: ICLR (2026)"},{"key":"36_CR17","unstructured":"Kim, M., Kim, J., Kang, U.: SynQ: accurate zero-shot quantization by synthesis-aware fine-tuning. In: ICLR (2025)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Kim, M., Lee, J., Kim, J., Yun, J., Kwon, Y., Kang, U.: LampQ: towards accurate layer-wise mixed precision quantization for vision transformers. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i7.37489"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Kim, M.: Zero-shot quantization: a comprehensive survey. In: IJCAI (2025)","DOI":"10.24963\/ijcai.2025\/1167"},{"key":"36_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Hard sample matters a lot in zero-shot quantization. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02339"},{"key":"36_CR22","doi-asserted-by":"publisher","unstructured":"Li, Y., Kim, Y., Lee, D., Kundu, S., Panda, P.: GenQ: quantization in low data regimes with generative synthetic data. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15071, pp. 216\u2013235. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72624-8_13","DOI":"10.1007\/978-3-031-72624-8_13"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S.I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Nagel, M.: Data-free quantization through weight equalization and bias correction. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00141"},{"key":"36_CR25","unstructured":"Nagel, M.: Up or down? Adaptive rounding for post-training quantization. In: ICML(2020)"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Park, S., Kim, M., Kang, U.: Unifying uniform and binary-coding quantization for accurate compression of large language models. In: ACL (2025)","DOI":"10.18653\/v1\/2025.acl-long.1382"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Park, S., Lee, S., Kim, J., Lee, J., Jo, H., Kang, U.: Accurate sublayer pruning for large language models by exploiting latency and tunability information. In: IJCAI (2025)","DOI":"10.24963\/ijcai.2025\/913"},{"key":"36_CR28","unstructured":"Park, S.: Accurate retraining-free pruning for pretrained encoder-based language models. In: ICLR (2024)"},{"key":"36_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-030-58526-6_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A-H Phan","year":"2020","unstructured":"Phan, A.-H., et al.: Stable low-rank tensor decomposition for compression of convolutional neural network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 522\u2013539. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_31"},{"issue":"4","key":"36_CR30","doi-asserted-by":"publisher","first-page":"e0265621","DOI":"10.1371\/journal.pone.0265621","volume":"17","author":"T Piao","year":"2022","unstructured":"Piao, T., Cho, I., Kang, U.: SensiMix: sensitivity-aware 8-bit index & 1-bit value mixed precision quantization for BERT compression. PLoS ONE 17(4), e0265621 (2022)","journal-title":"PLoS ONE"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Qian, B.: Adaptive data-free quantization. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00769"},{"key":"36_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNet V2: inverted residuals and linear bottlenecks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"36_CR33","doi-asserted-by":"crossref","unstructured":"Schotth\u00f6fer, S., Zangrando, E., Kusch, J., Ceruti, G., Tudisco, F.: Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations. In: NeurIPS (2022)","DOI":"10.52202\/068431-1458"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Son, W., Na, J., Choi, J., Hwang, W.: Densely guided knowledge distillation using multiple teacher assistants. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"36_CR35","doi-asserted-by":"publisher","unstructured":"Wang, Y., Cheng, L., Duan, M., Wang, Y., Feng, Z., Kong, S.: Improving knowledge distillation via regularizing feature norm and direction. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15082. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72691-0_2","DOI":"10.1007\/978-3-031-72691-0_2"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, C., Wang, X.: Convolutional neural network pruning with structural redundancy reduction (2021)","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"36_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58610-2_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Xu","year":"2020","unstructured":"Xu, S., Li, H., Zhuang, B., Liu, J., Cao, J., Liang, C., Tan, M.: Generative low-bitwidth data free quantization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 1\u201317. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_1"},{"key":"36_CR38","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., Zhang, Q.: Cross-image relational knowledge distillation for semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Ye, X., et al.: Accelerating CNN training by pruning activation gradients (2020)","DOI":"10.1007\/978-3-030-58595-2_20"},{"key":"36_CR40","doi-asserted-by":"crossref","unstructured":"Yin, H., et al.: Dreaming to distill: data-free knowledge transfer via DeepInversion. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"36_CR41","unstructured":"Yoo, J., Cho, M., Kim, T., Kang, U.: Knowledge extraction with no observable data. In: NeurIPS (2019)"},{"key":"36_CR42","doi-asserted-by":"crossref","unstructured":"Yun, J., Lee, J., Kim, J., Kim, M., Song, J., Kang, U.: SharVeT: similarity-aware parameter sharing with vector-based tuning for efficient LLM compression. In: ACL (2026)","DOI":"10.18653\/v1\/2026.acl-long.2213"},{"key":"36_CR43","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: IntraQ: learning synthetic images with intra-class heterogeneity for zero-shot network quantization. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01202"}],"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\/978-3-032-37211-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:45:32Z","timestamp":1789022732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37211-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372109","9783032372116"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37211-6_36","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":"11 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"}}]}}