{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T15:36:59Z","timestamp":1779896219514,"version":"3.53.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200823","type":"print"},{"value":"9783031200830","type":"electronic"}],"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_32","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:46:34Z","timestamp":1667418394000},"page":"536-552","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Towards Accurate Binary Neural Networks via\u00a0Modeling Contextual Dependencies"],"prefix":"10.1007","author":[{"given":"Xingrun","family":"Xing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangguang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenrui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yalong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunlei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"32_CR1","unstructured":"Bethge, J., Bartz, C., Yang, H., Chen, Y., Meinel, C.: MeliusNet: can binary neural networks achieve mobileNet-level accuracy? arXiv preprint arXiv:2001.05936 (2020)"},{"key":"32_CR2","unstructured":"Chen, S., Xie, E., Ge, C., Liang, D., Luo, P.: CycleMLP: a MLP-like architecture for dense prediction. arXiv preprint arXiv:2107.10224 (2021)"},{"key":"32_CR3","unstructured":"Chu, X., et al.: Twins: revisiting spatial attention design in vision transformers (2021)"},{"key":"32_CR4","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830 (2016)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: UP-DETR: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"32_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"32_CR8","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Ji, M., Shin, S., Hwang, S., Park, G., Moon, I.C.: Refine myself by teaching myself: feature refinement via self-knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10664\u201310673 (2021)","DOI":"10.1109\/CVPR46437.2021.01052"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, X., Wang, N., Xin, J., Li, K., Yang, X., Gao, X.: Training binary neural network without batch normalization for image super-resolution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1700\u20131707 (2021)","DOI":"10.1609\/aaai.v35i2.16263"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Joo, D., Yi, E., Baek, S., Kim, J.: Linearly replaceable filters for deep network channel pruning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 8021\u20138029 (2021)","DOI":"10.1609\/aaai.v35i9.16978"},{"key":"32_CR12","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: stanford dogs. In: Proceedings CVPR Workshop on Fine-Grained Visual Categorization (FGVC), vol. 2. Citeseer (2011)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., Ham, B.: Network quantization with element-wise gradient scaling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6448\u20136457 (2021)","DOI":"10.1109\/CVPR46437.2021.00638"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"32_CR16","unstructured":"Lin, M., et al.: Rotated binary neural network. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"32_CR17","unstructured":"Lin, X., Zhao, C., Pan, W.: Towards accurate binary convolutional neural network. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Liu, C., Chen, P., Zhuang, B., Shen, C., Zhang, B., Ding, W.: SA-BNN: state-aware binary neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2091\u20132099 (2021)","DOI":"10.1609\/aaai.v35i3.16306"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., Ye, M., Zhou, D., Liu, Q.: Post-training quantization with multiple points: mixed precision without mixed precision. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 8697\u20138705 (2021)","DOI":"10.1609\/aaai.v35i10.17054"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"32_CR21","unstructured":"Liu, Z., Shen, Z., Li, S., Helwegen, K., Huang, D., Cheng, K.T.: How do Adam and training strategies help BNNs optimization? In: International Conference on Machine Learning. PMLR (2021)"},{"key":"32_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-030-58568-6_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Shen, Z., Savvides, M., Cheng, K.-T.: ReActNet: towards precise binary neural network with generalized activation functions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 143\u2013159. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_9"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.T.: Bi-Real Net: enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm. In: Proceedings of the European conference on computer vision (ECCV), pp. 722\u2013737 (2018)","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Li\u2019an Zhuo, B.Z., Chen, H., Yang, L., Chen, C., Zhu, Y., Doermann, D.: CP-NAS: child-parent neural architecture search for 1-bit CNNs. In: IJCAI (2020)","DOI":"10.24963\/ijcai.2020\/144"},{"key":"32_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"32_CR26","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"32_CR27","unstructured":"Martinez, B., Yang, J., Bulat, A., Tzimiropoulos, G.: Training binary neural networks with real-to-binary convolutions. arXiv preprint arXiv:2003.11535 (2020)"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Qin, H., et al.: Forward and backward information retention for accurate binary neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2250\u20132259 (2020)","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"32_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-46493-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Rastegari","year":"2016","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525\u2013542. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32"},{"issue":"3","key":"32_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetv 2: 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":"32_CR33","doi-asserted-by":"crossref","unstructured":"Song, L., Wu, J., Yang, M., Zhang, Q., Li, Y., Yuan, J.: Robust knowledge transfer via hybrid forward on the teacher-student model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2558\u20132566 (2021)","DOI":"10.1609\/aaai.v35i3.16358"},{"key":"32_CR34","unstructured":"Tolstikhin, I., et al.: MLP-mixer: an all-MLP architecture for vision. arXiv preprint arXiv:2105.01601 (2021)"},{"key":"32_CR35","unstructured":"Touvron, H., et al.: ResMLP: feedforward networks for image classification with data-efficient training. ArXiv abs\/2105.03404 (2021)"},{"key":"32_CR36","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, vol. 139, pp. 10347\u201310357 (2021)"},{"key":"32_CR37","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Wu, B., et al.: Shift: a zero flop, zero parameter alternative to spatial convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9127\u20139135 (2018)","DOI":"10.1109\/CVPR.2018.00951"},{"key":"32_CR39","unstructured":"Xiao, T., Dollar, P., Singh, M., Mintun, E., Darrell, T., Girshick, R.: Early convolutions help transformers see better. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"32_CR40","first-page":"25553","volume":"34","author":"Y Xu","year":"2021","unstructured":"Xu, Y., Han, K., Xu, C., Tang, Y., Xu, C., Wang, Y.: Learning frequency domain approximation for binary neural networks. Adv. Neural. Inf. Process. Syst. 34, 25553\u201325565 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR41","doi-asserted-by":"crossref","unstructured":"Yamamoto, K.: Learnable companding quantization for accurate low-bit neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5029\u20135038 (2021)","DOI":"10.1109\/CVPR46437.2021.00499"},{"key":"32_CR42","first-page":"4091","volume":"33","author":"Z Yang","year":"2020","unstructured":"Yang, Z., et al.: Searching for low-bit weights in quantized neural networks. Adv. Neural. Inf. Process. Syst. 33, 4091\u20134102 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR43","doi-asserted-by":"crossref","unstructured":"Yu, T., Li, X., Cai, Y., Sun, M., Li, P.: S2-MLP: spatial-shift MLP architecture for vision. arXiv preprint arXiv:2106.07477 (2021)","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yang, J., Ye, D., Hua, G.: LQ-Nets: learned quantization for highly accurate and compact deep neural networks. In: Proceedings of the European conference on computer vision (ECCV), pp. 365\u2013382 (2018)","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"32_CR45","unstructured":"Zhang, Z., Zhang, H., Zhao, L., Chen, T., Pfister, T.: Aggregating nested transformers. arXiv preprint arXiv:2105.12723 (2021)"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, K., et al.: Distribution adaptive int8 quantization for training CNNs. In: Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i4.16462"},{"key":"32_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"32_CR48","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv: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_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:06:43Z","timestamp":1710331603000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20083-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200823","9783031200830"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20083-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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)"}}]}}