{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:16:18Z","timestamp":1743131778314,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200823"},{"type":"electronic","value":"9783031200830"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20083-0_13","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:46:34Z","timestamp":1667418394000},"page":"206-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Symmetry Regularization and\u00a0Saturating Nonlinearity for\u00a0Robust Quantization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3818-4584","authenticated-orcid":false,"given":"Sein","family":"Park","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2046-2419","authenticated-orcid":false,"given":"Yeongsang","family":"Jang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-9819","authenticated-orcid":false,"given":"Eunhyeok","family":"Park","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"13_CR1","unstructured":"Alizadeh, M., Behboodi, A., van Baalen, M., Louizos, C., Blankevoort, T., Welling, M.: Gradient l1 regularization for quantization robustness. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, 26\u201330 April 2020. OpenReview.net (2020). https:\/\/openreview.net\/forum?id=ryxK0JBtPr"},{"key":"13_CR2","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D.: ACIQ: analytical clipping for integer quantization of neural networks. CoRR abs\/1810.05723 (2018). http:\/\/arxiv.org\/abs\/1810.05723"},{"key":"13_CR3","unstructured":"Banner, R., Nahshan, Y., Soudry, D.: Post training 4-bit quantization of convolutional networks for rapid-deployment. In: NeurIPS (2019)"},{"key":"13_CR4","unstructured":"Brock, A., De, S., Smith, S.L.: Characterizing signal propagation to close the performance gap in unnormalized ResNets. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=IX3Nnir2omJ"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Y., Yao, Z., Dong, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: ZeroQ: a novel zero shot quantization framework. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13166\u201313175 (2020)","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"13_CR6","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.J., Srinivasan, V., Gopalakrishnan, K.: PACT: parameterized clipping activation for quantized neural networks (2018). https:\/\/openreview.net\/forum?id=By5ugjyCb"},{"key":"13_CR7","unstructured":"Dong, Z., Yao, Z., Arfeen, D., Gholami, A., Mahoney, M.W., Keutzer, K.: HAWQ-V2: hessian aware trace-weighted quantization of neural networks. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 18518\u201318529. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/d77c703536718b95308130ff2e5cf9ee-Paper.pdf"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Dong, Z., Yao, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: HAWQ: hessian aware quantization of neural networks with mixed-precision. In; 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 293\u2013302 (2019)","DOI":"10.1109\/ICCV.2019.00038"},{"key":"13_CR9","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned step size quantization. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=rkgO66VKDS"},{"key":"13_CR10","unstructured":"Finkelstein, A., Almog, U., Grobman, M.: Fighting quantization bias with bias. arXiv preprint arXiv:1906.03193 (2019)"},{"key":"13_CR11","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=6Tm1mposlrM"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Han, T., Li, D., Liu, J., Tian, L., Shan, Y.: Improving low-precision network quantization via bin regularization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5261\u20135270 (2021)","DOI":"10.1109\/ICCV48922.2021.00521"},{"key":"13_CR13","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 770\u2013778. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR14","unstructured":"Hoffman, J., Roberts, D.A., Yaida, S.: Robust learning with Jacobian regularization (2020). https:\/\/openreview.net\/forum?id=ryl-RTEYvB"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"13_CR16","unstructured":"Hubara, I., Nahshan, Y., Hanani, Y., Banner, R., Soudry, D.: Accurate post training quantization with small calibration sets. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 139, pp. 4466\u20134475. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/hubara21a.html"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"13_CR18","doi-asserted-by":"publisher","unstructured":"Jang, J., et al.: Sparsity-aware and re-configurable NPU architecture for Samsung flagship mobile SoC. In: 48th ACM\/IEEE Annual International Symposium on Computer Architecture, ISCA 2021, Valencia, Spain, 14\u201318 June 2021, pp. 15\u201328. IEEE (2021). https:\/\/doi.org\/10.1109\/ISCA52012.2021.00011","DOI":"10.1109\/ISCA52012.2021.00011"},{"key":"13_CR19","doi-asserted-by":"publisher","unstructured":"Jouppi, N.P., et al.: Ten lessons from three generations shaped Google\u2019s TPUv4i: industrial product. In: 48th ACM\/IEEE Annual International Symposium on Computer Architecture, ISCA 2021, Valencia, Spain, 14\u201318 June 2021, pp. 1\u201314. IEEE (2021). https:\/\/doi.org\/10.1109\/ISCA52012.2021.00010","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Jung, S.H., et al.: Learning to quantize deep networks by optimizing quantization intervals with task loss. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4345\u20134354 (2019)","DOI":"10.1109\/CVPR.2019.00448"},{"key":"13_CR21","unstructured":"Kwon, J., Kim, J., Park, H., Choi, I.K.: ASAM: adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 5905\u20135914. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/kwon21b.html"},{"key":"13_CR22","unstructured":"Lee, J.H., Ha, S., Choi, S., Lee, W.J., Lee, S.: Quantization for rapid deployment of deep neural networks (2019). https:\/\/openreview.net\/forum?id=HkzZBi0cFQ"},{"key":"13_CR23","unstructured":"Li, Y., et al.: BRECQ: pushing the limit of post-training quantization by block reconstruction. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=POWv6hDd9XH"},{"key":"13_CR24","unstructured":"Lin, J., Gan, C., Han, S.: Defensive quantization: when efficiency meets robustness. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=ryetZ20ctX"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Nagel, M., van Baalen, M., Blankevoort, T., Welling, M.: Data-free quantization through weight equalization and bias correction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1325\u20131334 (2019)","DOI":"10.1109\/ICCV.2019.00141"},{"key":"13_CR26","unstructured":"Nahshan, Y., et al.: Loss aware post-training quantization. arXiv abs\/1911.07190 (2021)"},{"key":"13_CR27","unstructured":"Int4 precision for AI inference (2019). https:\/\/devblogs.nvidia.com\/int4-for-ai-inference\/. Accessed 16 Nov 2021"},{"key":"13_CR28","unstructured":"NVIDIA a100 tensor core GPU architecture (2020). https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf. Accessed 16 Nov 2021"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Park, E., Kim, D., Yoo, S.: Energy-efficient neural network accelerator based on outlier-aware low-precision computation. In: International Symposium on Computer Architecture (ISCA) (2018)","DOI":"10.1109\/ISCA.2018.00063"},{"key":"13_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/978-3-030-58539-6_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"E Park","year":"2020","unstructured":"Park, E., Yoo, S.: PROFIT: a novel training method for sub-4-bit MobileNet models. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 430\u2013446. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_26"},{"key":"13_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1007\/978-3-030-01225-0_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"E Park","year":"2018","unstructured":"Park, E., Yoo, S., Vajda, P.: Value-aware quantization for training and inference of neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 608\u2013624. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_36"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Sharma, H., et al.: Bit fusion: bit-level dynamically composable architecture for accelerating deep neural networks. In: International Symposium on Computer Architecture (ISCA) (2018)","DOI":"10.1109\/ISCA.2018.00069"},{"key":"13_CR34","unstructured":"Shkolnik, M., et al.: Robust quantization: one model to rule them all. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H.T. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December, pp. 6\u201312, 2020. Virtual (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/3948ead63a9f2944218de038d8934305-Abstract.html"},{"key":"13_CR35","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"13_CR36","unstructured":"Snapdragon neural processing engine SDK (2017). https:\/\/developer.qualcomm.com\/docs\/snpe\/index.html. Accessed 16 Nov 2021"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Song, J., et al.: 7.1 an 11.5 TOPS\/W 1024-MAC butterfly structure dual-core sparsity-aware neural processing unit in 8nm flagship mobile SoC. In: International Solid-State Circuits Conference (ISSCC) (2019)","DOI":"10.1109\/ISSCC.2019.8662476"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR) (2015). http:\/\/arxiv.org\/abs\/1409.4842","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"13_CR39","unstructured":"Tulloch, A., Jia, Y.: High performance ultra-low-precision convolutions on mobile devices. arXiv:1712.02427 (2017)"},{"key":"13_CR40","unstructured":"Tulloch, A., Jia, Y.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)"},{"key":"13_CR41","unstructured":"Wei, X., Gong, R., Li, Y., Liu, X., Yu, F.: QDrop: randomly dropping quantization for extremely low-bit post-training quantization. In: International Conference on Learning Representations (2022)"},{"key":"13_CR42","unstructured":"Wu, H.: NVIDIA low precision inference on GPU. In: GPU Technology Conference (2019)"},{"key":"13_CR43","unstructured":"Wu, H., Judd, P., Zhang, X., Isaev, M., Micikevicius, P.: Integer quantization for deep learning inference: principles and empirical evaluation. CoRR abs\/2004.09602 (2020). https:\/\/arxiv.org\/abs\/2004.09602"},{"key":"13_CR44","unstructured":"Yao, Z., et al.: HAWQV3: dyadic neural network quantization. In: ICML (2021)"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Yu, H., Wen, T., Cheng, G., Sun, J., Han, Q., Shi, J.: Low-bit quantization needs good distribution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 680\u2013681 (2020)","DOI":"10.1109\/CVPRW50498.2020.00348"},{"key":"13_CR46","unstructured":"Zhao, R., Hu, Y., Dotzel, J., Sa, C.D., Zhang, Z.: Improving neural network quantization without retraining using outlier channel splitting. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, California, USA, 9\u201315 June 2019. Proceedings of Machine Learning Research, vol. 97, pp. 7543\u20137552. PMLR (2019). http:\/\/proceedings.mlr.press\/v97\/zhao19c.html"},{"key":"13_CR47","unstructured":"Zhou, S., Ni, Z., Zhou, X., Wen, H., Wu, Y., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv abs\/1606.06160 (2016)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20083-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:56:49Z","timestamp":1710331009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20083-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200823","9783031200830"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20083-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}