{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T11:37:01Z","timestamp":1776166621402,"version":"3.50.1"},"reference-count":96,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"name":"IPCEI Microelectronics and Connectivity"},{"name":"French Public Authorities"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    Binary Neural Networks (BNNs) are a promising approach to enable Artificial Neural Network (ANN) implementation on ultra-low power edge devices. Such devices may compute data in highly dynamic environments, in which the classes targeted for inference can evolve or even novel classes may appear, requiring continual learning. Class Incremental Learning (CIL) is an important type of continual learning for classification problems, yet it has been scarcely addressed in the context of BNNs. Furthermore, most of existing BNNs models are not fully binary, as they require several real-valued network layers, at the input, the output, and for batch normalization. This article goes a step further, enabling class incremental learning in Fully-Binarized NNs (FBNNs) through four main contributions. We firstly revisit the FBNN design and its training procedure that is suitable to CIL. Secondly, we explore loss balancing, a method to tradeoff the performance of past and current classes. Thirdly, we propose a semi-supervised method to pre-train the feature extractor of the FBNN for transferable representations. Fourthly, two conventional CIL methods,\n                    <jats:italic toggle=\"yes\">i<\/jats:italic>\n                    .\n                    <jats:italic toggle=\"yes\">e<\/jats:italic>\n                    ., Latent and Native replay, are thoroughly compared. These contributions are exemplified first on the CIFAR100 dataset, before being scaled up to the CORE50 continual learning benchmark. The final results based on our 3Mb FBNN on CORE50 , exhibit performance that is at par with, or better than conventional, larger, real-valued NN models.\n                  <\/jats:p>","DOI":"10.1145\/3794851","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:11:00Z","timestamp":1771243860000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks"],"prefix":"10.1145","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5109-6602","authenticated-orcid":false,"given":"Yanis","family":"Basso-Bert","sequence":"first","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, CEA List","place":["Grenoble, France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2400-165X","authenticated-orcid":false,"given":"Anca","family":"Molnos","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, CEA List","place":["Grenoble, France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7260-2786","authenticated-orcid":false,"given":"Romain","family":"Lemaire","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, CEA List","place":["Grenoble, France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8925-0441","authenticated-orcid":false,"given":"William","family":"Guicquero","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, CEA Leti","place":["Grenoble, France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0145-2186","authenticated-orcid":false,"given":"Antoine","family":"Dupret","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, CEA Leti","place":["Grenoble, France"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,14]]},"reference":[{"issue":"7","key":"e_1_3_1_2_2","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1109\/TVLSI.2022.3163233","article-title":"MOL-based in-memory computing of binary neural networks","volume":"30","author":"Ali Khaled Alhaj","year":"2022","unstructured":"Khaled Alhaj Ali, Amer Baghdadi, Elsa Dupraz, Mathieu L\u00e9onardon, Mostafa Rizk, and Jean-Philippe Diguet. 2022. MOL-based in-memory computing of binary neural networks. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 30, 7 (July2022), 869\u2013880.","journal-title":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2869150"},{"key":"e_1_3_1_4_2","unstructured":"Tom Bannink Arash Bakhtiari Adam Hillier Lukas Geiger Tim de Bruin Leon Overweel Jelmer Neeven and Koen Helwegen. 2020. Larq compute engine: Design benchmark and deploy state-of-the-art binarized neural networks. arXiv:2011.09398. Retrieved from https:\/\/arxiv.org\/abs\/2011.09398"},{"key":"e_1_3_1_5_2","first-page":"1","volume-title":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","author":"Basso-Bert Yanis","year":"2024","unstructured":"Yanis Basso-Bert, William Guicquero, Anca Molnos, Romain Lemaire, and Antoine Dupret. 2024. On Class-incremental learning for fully binarized convolutional neural networks. In 2024 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1\u20135."},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.neunet.2020.12.003","article-title":"A comprehensive study of class incremental learning algorithms for visual tasks","volume":"135","author":"Belouadah Eden","year":"2021","unstructured":"Eden Belouadah, Adrian Popescu, and Ioannis Kanellos. 2021. A comprehensive study of class incremental learning algorithms for visual tasks. Neural Networks 135 (2021), 38\u201354.","journal-title":"Neural Networks"},{"key":"e_1_3_1_7_2","volume-title":"ECCV Workshops","author":"Belouadah Eden","year":"2018","unstructured":"Eden Belouadah and Adrian Daniel Popescu. 2018. DeeSIL: Deep-shallow incremental learning. In ECCV Workshops."},{"key":"e_1_3_1_8_2","unstructured":"Yoshua Bengio Nicholas L\u00e9onard and Aaron C. Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv:1308.3432. Retrieved from https:\/\/arxiv.org\/abs\/1308.3432"},{"issue":"2","key":"e_1_3_1_9_2","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1109\/JSSC.2022.3194098","article-title":"A 389 tops\/w, always on region proposal integrated circuit using in-memory computing in 65 nm CMOS","volume":"58","author":"Bose Sumon Kumar","year":"2023","unstructured":"Sumon Kumar Bose and Arindam Basu. 2023. A 389 tops\/w, always on region proposal integrated circuit using in-memory computing in 65 nm CMOS. IEEE Journal of Solid-State Circuits 58, 2 (Feb.2023), 554\u2013568.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"e_1_3_1_10_2","first-page":"15920","article-title":"Dark experience for general continual learning: a strong, simple baseline","volume":"33","author":"Buzzega Pietro","year":"2020","unstructured":"Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, and Simone Calderara. 2020. Dark experience for general continual learning: a strong, simple baseline. Advances in Neural Information Processing Systems 33, Article 1335 (2020), 15920\u201315930.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_11_2","first-page":"2180","article-title":"Rethinking experience replay: A bag of tricks for continual learning","author":"Buzzega Pietro","year":"2020","unstructured":"Pietro Buzzega, Matteo Boschini, Angelo Porrello, and Simone Calderara. 2020. Rethinking experience replay: A bag of tricks for continual learning. 2020 25th International Conference on Pattern Recognition (ICPR) (2020), 2180\u20132187.","journal-title":"2020 25th International Conference on Pattern Recognition (ICPR)"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/ISSCC42615.2023.10067339","volume-title":"2023 IEEE International Solid-State Circuits Conference (ISSCC)","author":"Cai Hao","year":"2023","unstructured":"Hao Cai, Zhongjian Bian, Yaoru Hou, Yongliang Zhou, Jia-le Cui, Yanan Guo, Xiaoyun Tian, Bo Liu, Xin Si, Zhen Wang et\u00a0al. 2023. A 28nm 2Mb STT-Mram computing-in-memory macro with a refined bit-cell and 22.4-41.5tops\/w for AI inference. In 2023 IEEE International Solid-State Circuits Conference (ISSCC). 500\u2013502. DOI:10.1109\/ISSCC42615.2023.10067339"},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/ISSCC42615.2023.10067339","volume-title":"2023 IEEE International Solid-State Circuits Conference (ISSCC)","author":"Cai Hao","year":"2023","unstructured":"Hao Cai, Zhongjian Bian, Yaoru Hou, Yongliang Zhou, Jia-le Cui, Yanan Guo, Xiaoyun Tian, Bo Liu, Xin Si, Zhen Wang et\u00a0al. 2023. A 28nm 2Mb STT-MRAM computing-in-memory macro with a refined bit-cell and 22.4-41.5tops\/w for AI inference. In 2023 IEEE International Solid-State Circuits Conference (ISSCC). 500\u2013502. DOI:10.1109\/ISSCC42615.2023.10067339"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2983648"},{"key":"e_1_3_1_15_2","unstructured":"Mathilde Caron Ishan Misra Julien Mairal Priya Goyal Piotr Bojanowski and Armand Joulin. 2020. Unsupervised learning of visual features by contrasting cluster assignments. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS\u201920). Curran Associates Inc. Vancouver BC Canada."},{"key":"e_1_3_1_16_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Castro Francisco M.","year":"2018","unstructured":"Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Cordelia Schmid, and Karteek Alahari. 2018. End-to-end incremental learning. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_1_17_2","first-page":"20127","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cha Sungmin","year":"2023","unstructured":"Sungmin Cha, Sungjun Cho, Dasol Hwang, Sunwon Hong, Moontae Lee, and Taesup Moon. 2023. Rebalancing batch normalization for exemplar-based class-incremental learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20127\u201320136."},{"key":"e_1_3_1_18_2","unstructured":"Arslan Chaudhry Marcus Rohrbach Mohamed Elhoseiny Thalaiyasingam Ajanthan Puneet Kumar Dokania Philip H. S. Torr and Marc\u2019Aurelio Ranzato. 2019. Continual learning with tiny episodic memories. arXiv:1902.10486. Retrieved from https:\/\/arxiv.org\/abs\/1902.10486"},{"key":"e_1_3_1_19_2","unstructured":"Arslan Chaudhry Marcus Rohrbach Mohamed Elhoseiny Thalaiyasingam Ajanthan Puneet K. Dokania Philip H. S. Torr and Marc\u2019Aurelio Ranzato. 2019. On tiny episodic memories in continual learning. arXiv:1902.10486. Retrieved from https:\/\/arxiv.org\/abs\/1902.10486"},{"key":"e_1_3_1_20_2","first-page":"4619","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Chen Tianlong","year":"2021","unstructured":"Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, and Zhangyang Wang. 2021. \u201cBNN - BN = ?\u201d: Training binary neural networks without batch normalization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 4619\u20134629."},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/JXCDC.2023.3320677"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/JXCDC.2023.3320677"},{"key":"e_1_3_1_23_2","volume-title":"Keras","author":"Chollet Francois","year":"2015","unstructured":"Francois Chollet et\u00a0al. 2015. Keras. Retrieved from https:\/\/github.com\/fchollet\/keras"},{"key":"e_1_3_1_24_2","first-page":"215","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","author":"Coates Adam","year":"2011","unstructured":"Adam Coates, Andrew Ng, and Honglak Lee. 2011. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 215\u2013223."},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/ISSCC42615.2023.10067588","volume-title":"2023 IEEE International Solid-State Circuits Conference (ISSCC)","author":"Garrett David","year":"2023","unstructured":"David Garrett, Youn Sung Park, Seongjong Kim, Jay Sharma, Wenbin Huang, Majid Shaghaghi, Vinay Parthasarathy, Stephen Gibellini, Stephen Bailey, Mallik Moturi, et\u00a0al. 2023. A 1mW always-on computer vision deep learning neural decision processor. In 2023 IEEE International Solid-State Circuits Conference (ISSCC). 8\u201310. DOI:10.1109\/ISSCC42615.2023.10067588"},{"key":"e_1_3_1_26_2","unstructured":"Spyros Gidaris Praveer Singh and Nikos Komodakis. 2018. Unsupervised representation learning by predicting image rotations. arXiv:1803.07728. Retrieved from https:\/\/arxiv.org\/abs\/1803.07728"},{"key":"e_1_3_1_27_2","first-page":"249","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS56072.2025.11044218"},{"issue":"12","key":"e_1_3_1_29_2","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1016\/j.tics.2020.09.004","article-title":"Embracing change: Continual learning in deep neural networks","volume":"24","author":"Hadsell Raia","year":"2020","unstructured":"Raia Hadsell, Dushyant Rao, Andrei A Rusu, and Razvan Pascanu. 2020. Embracing change: Continual learning in deep neural networks. Trends in Cognitive Sciences 24, 12 (2020), 1028\u20131040.","journal-title":"Trends in Cognitive Sciences"},{"key":"e_1_3_1_30_2","first-page":"9729","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 9729\u20139738."},{"key":"e_1_3_1_31_2","first-page":"770","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770\u2013778."},{"key":"e_1_3_1_32_2","unstructured":"Lu Hou Quanming Yao and James Tin-Yau Kwok. 2016. Loss-aware Binarization of Deep Networks. arXiv:1611.01600. Retrieved from https:\/\/arxiv.org\/abs\/1611.01600"},{"key":"e_1_3_1_33_2","article-title":"Binarized neural networks","volume":"29","author":"Hubara Itay","year":"2016","unstructured":"Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks. Advances in Neural Information Processing Systems (NIPS) 29 (2016).","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"e_1_3_1_34_2","first-page":"448","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML)","volume":"37","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning (ICML), Vol. 37. 448\u2013456."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Ahmet Iscen Jeffrey Zhang Svetlana Lazebnik and Cordelia Schmid. 2020. Memory-efficient incremental learning through feature adaptation. Springer-Verlag Berlin Heidelberg 699\u2013715. DOI:10.1007\/978-3-030-58517-4_41","DOI":"10.1007\/978-3-030-58517-4_41"},{"issue":"13","key":"e_1_3_1_36_2","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick James","year":"2017","unstructured":"James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et\u00a0al. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences 114, 13 (2017), 3521\u20133526.","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"13","key":"e_1_3_1_37_2","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick James","year":"2017","unstructured":"James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et\u00a0al.. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences 114, 13 (March2017), 3521\u20133526.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"e_1_3_1_38_2","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:18268744"},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","first-page":"2416","DOI":"10.1109\/EMBC48229.2022.9871690","volume-title":"2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","author":"Sah Ramesh Kumar","year":"2022","unstructured":"Ramesh Kumar Sah, Seyed Iman Mirzadeh, and Hassan Ghasemzadeh. 2022. Continual learning for activity recognition. In 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 2416\u20132420. DOI:10.1109\/EMBC48229.2022.9871690"},{"issue":"1","key":"e_1_3_1_40_2","doi-asserted-by":"crossref","first-page":"2549","DOI":"10.1038\/s41467-021-22768-y","article-title":"Synaptic metaplasticity in binarized neural networks","volume":"12","author":"Laborieux Axel","year":"2021","unstructured":"Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin, and Damien Querlioz. 2021. Synaptic metaplasticity in binarized neural networks. Nature Communications 12, 1 (May2021), 2549.","journal-title":"Nature Communications"},{"key":"e_1_3_1_41_2","unstructured":"Min Lin Qiang Chen and Shuicheng Yan. 2013. Network in network. arXiv:1312.4400. Retrieved from https:\/\/arxiv.org\/abs\/1312.4400"},{"key":"e_1_3_1_42_2","first-page":"202","article-title":"Bi-Real Net: Binarizing deep network towards real-network performance","volume":"128","author":"Liu Zechun","year":"2018","unstructured":"Zechun Liu, Wenhan Luo, Baoyuan Wu, Xin Yang, W. Liu, and K. Cheng. 2018. Bi-Real Net: Binarizing deep network towards real-network performance. International Journal of Computer Vision 128 (2018), 202\u2013219.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_3_1_43_2","first-page":"143","volume-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16","author":"Liu Zechun","year":"2020","unstructured":"Zechun Liu, Zhiqiang Shen, Marios Savvides, and Kwang-Ting Cheng. 2020. Reactnet: Towards precise binary neural network with generalized activation functions. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16. Springer, 143\u2013159."},{"key":"e_1_3_1_44_2","series-title":"Proceedings of Machine Learning Research","first-page":"17","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","volume":"78","author":"Lomonaco Vincenzo","year":"2017","unstructured":"Vincenzo Lomonaco and Davide Maltoni. 2017. CORe50: A new dataset and benchmark for continuous object recognition. In Proceedings of the 1st Annual Conference on Robot Learning(Proceedings of Machine Learning Research, Vol. 78), Sergey Levine, Vincent Vanhoucke, and Ken Goldberg (Eds.). PMLR, 17\u201326."},{"key":"e_1_3_1_45_2","first-page":"3","volume-title":"CVPR Workshops","author":"Lomonaco Vincenzo","year":"2020","unstructured":"Vincenzo Lomonaco, Davide Maltoni, Lorenzo Pellegrini, et\u00a0al. 2020. Rehearsal-Free continual learning over small Non-IID batches. In CVPR Workshops, Vol. 1. 3."},{"key":"e_1_3_1_46_2","series-title":"NIPS\u201917","first-page":"6470","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lopez-Paz David","year":"2017","unstructured":"David Lopez-Paz and Marc\u2019Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS\u201917). Curran Associates Inc., Red Hook, NY, USA, 6470\u20136479."},{"key":"e_1_3_1_47_2","first-page":"5704","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ma Ruichen","year":"2024","unstructured":"Ruichen Ma, Guanchao Qiao, Yian Liu, Liwei Meng, Ning Ning, Yang Liu, and Shaogang Hu. 2024. A&B BNN: Add&Bit-Operation-Only hardware-friendly binary neural network. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5704\u20135713."},{"key":"e_1_3_1_48_2","doi-asserted-by":"crossref","first-page":"3443","DOI":"10.1109\/CVPRW56347.2022.00388","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Machireddy Amrutha","year":"2022","unstructured":"Amrutha Machireddy, Ranganath Krishnan, Nilesh Ahuja, and Omesh Tickoo. 2022. Continual active adaptation to evolving distributional shifts. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 3443\u20133449. DOI:10.1109\/CVPRW56347.2022.00388"},{"key":"e_1_3_1_49_2","first-page":"3513","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Mittal Sudhanshu","year":"2021","unstructured":"Sudhanshu Mittal, Silvio Galesso, and Thomas Brox. 2021. Essentials for class incremental learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 3513\u20133522."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED57927.2023.10129322"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3205029"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3145024"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS55645.2022.9919206"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9937290"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSSC.2022.3161592"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2024.3377356"},{"key":"e_1_3_1_57_2","doi-asserted-by":"crossref","first-page":"10203","DOI":"10.1109\/IROS45743.2020.9341460","volume-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Pellegrini Lorenzo","year":"2020","unstructured":"Lorenzo Pellegrini, Gabriele Graffieti, Vincenzo Lomonaco, and Davide Maltoni. 2020. Latent replay for real-time continual learning. In 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 10203\u201310209. DOI:10.1109\/IROS45743.2020.9341460"},{"key":"e_1_3_1_58_2","article-title":"DualNet: Continual learning, fast and slow","volume":"34","author":"Pham Quang","year":"2021","unstructured":"Quang Pham, Chenghao Liu, and Steven Hoi. 2021. DualNet: Continual learning, fast and slow. Advances in Neural Information Processing Systems 34 (2021), 16131\u201316144.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_59_2","volume-title":"International Conference on Learning Representations","author":"Pham Quang","year":"2021","unstructured":"Quang Pham, Chenghao Liu, Doyen Sahoo, and Hoi Steven. 2021. Contextual transformation networks for online continual learning. In International Conference on Learning Representations."},{"key":"e_1_3_1_60_2","first-page":"55","volume-title":"Neural Networks: Tricks of the Trade","author":"Prechelt Lutz","year":"2002","unstructured":"Lutz Prechelt. 2002. Early stopping-but when? In Neural Networks: Tricks of the Trade. Springer, 55\u201369."},{"key":"e_1_3_1_61_2","doi-asserted-by":"crossref","first-page":"107281","DOI":"10.1016\/j.patcog.2020.107281","article-title":"Binary neural networks: A survey","volume":"105","author":"Qin Haotong","year":"2020","unstructured":"Haotong Qin, Ruihao Gong, Xianglong Liu, Xiao Bai, Jingkuan Song, and Nicu Sebe. 2020. Binary neural networks: A survey. Pattern Recognition 105 (Sept.2020), 107281.","journal-title":"Pattern Recognition"},{"key":"e_1_3_1_62_2","doi-asserted-by":"crossref","first-page":"107281","DOI":"10.1016\/j.patcog.2020.107281","article-title":"Binary neural networks: A survey","volume":"105","author":"Qin Haotong","year":"2020","unstructured":"Haotong Qin, Ruihao Gong, Xianglong Liu, Xiao Bai, Jingkuan Song, and Nicu Sebe. 2020. Binary neural networks: A survey. Pattern Recognition 105 (2020), 107281.","journal-title":"Pattern Recognition"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3394390"},{"key":"e_1_3_1_64_2","first-page":"525","volume-title":"European Conference on Computer Vision","author":"Rastegari Mohammad","year":"2016","unstructured":"Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi. 2016. Xnor-net: Imagenet classification using binary convolutional neural networks. In European Conference on Computer Vision. Springer, 525\u2013542."},{"key":"e_1_3_1_65_2","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1037\/0033-295X.97.2.285","article-title":"Connectionist models of recognition memory: constraints imposed by learning and forgetting functions.","volume":"97","author":"Ratcliff Roger","year":"1990","unstructured":"Roger Ratcliff. 1990. Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychological Review 97 2 (1990), 285\u2013308.","journal-title":"Psychological Review"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3121554"},{"key":"e_1_3_1_67_2","doi-asserted-by":"crossref","first-page":"5533","DOI":"10.1109\/CVPR.2017.587","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Rebuffi Sylvestre-Alvise","year":"2017","unstructured":"Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H. Lampert. 2017. iCaRL: Incremental classifier and representation learning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5533\u20135542. DOI:10.1109\/CVPR.2017.587"},{"key":"e_1_3_1_68_2","first-page":"2980","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Ross T-YLPG","year":"2017","unstructured":"T-YLPG Ross and GKHP Doll\u00e1r. 2017. Focal loss for dense object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2980\u20132988."},{"key":"e_1_3_1_69_2","unstructured":"Andrei A Rusu Neil C Rabinowitz Guillaume Desjardins Hubert Soyer James Kirkpatrick Koray Kavukcuoglu Razvan Pascanu and Raia Hadsell. 2016. Progressive Neural Networks. arXiv:1606.04671. Retrieved from https:\/\/arxiv.org\/abs\/1606.04671"},{"key":"e_1_3_1_70_2","doi-asserted-by":"crossref","first-page":"27546","DOI":"10.1109\/ACCESS.2023.3258360","article-title":"A systematic literature review on binary neural networks","volume":"11","author":"Sayed Ratshih","year":"2023","unstructured":"Ratshih Sayed, Haytham Azmi, Heba Shawkey, A. H. Khalil, and Mohamed Refky. 2023. A systematic literature review on binary neural networks. IEEE Access 11 (2023), 27546\u201327578.","journal-title":"IEEE Access"},{"key":"e_1_3_1_71_2","first-page":"1","volume-title":"2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)","author":"Shahroodi Taha","year":"2023","unstructured":"Taha Shahroodi, Raphael Cardoso, Mahdi Zahedi, Stephan Wong, Alberto Bosio, Ian O\u2019Connor, and Said Hamdioui. 2023. Lightspeed binary neural networks using optical phase-change materials. In 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE). 1\u20132. DOI:10.23919\/DATE56975.2023.10137229"},{"key":"e_1_3_1_72_2","first-page":"1","volume-title":"2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)","author":"Shahroodi Taha","year":"2023","unstructured":"Taha Shahroodi, Raphael Cardoso, Mahdi Zahedi, Stephan Wong, Alberto Bosio, Ian O\u2019Connor, and Said Hamdioui. 2023. Lightspeed binary neural networks using optical phase-change materials. In 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE). 1\u20132. DOI:10.23919\/DATE56975.2023.10137229"},{"key":"e_1_3_1_73_2","first-page":"2165","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Shen Zhiqiang","year":"2021","unstructured":"Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang, Kwang-Ting Cheng, and Marios Savvides. 2021. S2-bnn: Bridging the gap between self-supervised real and 1-bit neural networks via guided distribution calibration. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2165\u20132174."},{"key":"e_1_3_1_74_2","article-title":"Continual learning with deep generative replay","volume":"30","author":"Shin Hanul","year":"2017","unstructured":"Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual learning with deep generative replay. Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1007\/S42979-022-01392-7"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3476988"},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3476988"},{"key":"e_1_3_1_78_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"31","author":"Tang Wei","year":"2017","unstructured":"Wei Tang, Gang Hua, and Liang Wang. 2017. How to train a compact binary neural network with high accuracy?. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31."},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","unstructured":"George K. Thiruvathukal Yung-Hsiang Lu Jaeyoun Kim Yiran Chen Bo Chen Amir Gholami Sehoon Kim Zhen Dong Zhewei Yao Michael W. Mahoney et\u00a0al. 2022. A survey of quantization methods for efficient neural network inference. (Jan.2022) 291\u2013326. Book Title: Low-Power Computer Vision Edition: 1 Publisher: Chapman and Hall\/CRC. DOI:10.1201\/9781003162810-13","DOI":"10.1201\/9781003162810-13"},{"key":"e_1_3_1_80_2","unstructured":"Gido M. van de Ven and Andreas Savas Tolias. 2019. Three scenarios for continual learning. arXiv:1904.07734. Retrieved from https:\/\/arxiv.org\/abs\/1904.07734"},{"key":"e_1_3_1_81_2","first-page":"1","volume-title":"2024 IEEE Symposium on VLSI Circuits","author":"Verdant Arnaud","year":"2024","unstructured":"Arnaud Verdant, William Guicquero, David Coriat, Guillaume Moritz, Nicolas Royer, S\u00e9bastien Thuries, Ana\u00efs Mollard, Vincent Teil, Yann Deprez, Gilles Monnot, et\u00a0al. 2024. A 450\u00b5W@50fps wake-up module featuring auto-bracketed 3-scale log-corrected pattern recognition and motion detection in a 1.5Mpix 8T global shutter imager. In 2024 IEEE Symposium on VLSI Circuits. 1\u20132."},{"key":"e_1_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSICircuits18222.2020.9162854"},{"key":"e_1_3_1_83_2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.5220\/0012269000003660","volume-title":"Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","author":"Vorabbi Lorenzo","year":"2024","unstructured":"Lorenzo Vorabbi, Davide Maltoni, Guido Borghi, and Stefano Santi. 2024. Enabling on-device continual learning with binary neural networks and latent replay:. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SCITEPRESS, Rome, Italy, 25\u201336. DOI:10.5220\/0012269000003660"},{"key":"e_1_3_1_84_2","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/978-3-031-51023-6_4","volume-title":"Image Analysis and Processing - ICIAP 2023 Workshops: Udine, Italy, September 11\u201315, 2023, Proceedings, Part I","author":"Vorabbi Lorenzo","year":"2024","unstructured":"Lorenzo Vorabbi, Davide Maltoni, and Stefano Santi. 2024. On-Device learning with binary neural networks. in Image Analysis and Processing - ICIAP 2023 Workshops: Udine, Italy, September 11\u201315, 2023, Proceedings, Part I (Udine, Italy). Springer-Verlag, Berlin, Heidelberg, 39\u201350. DOI:10.1007\/978-3-031-51023-6_4"},{"key":"e_1_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3510295"},{"key":"e_1_3_1_86_2","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1109\/CVPR.2019.00046","article-title":"Large scale incremental learning","author":"Wu Yue","year":"2019","unstructured":"Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Raymond Fu. 2019. Large scale incremental learning. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 374\u2013382.","journal-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"e_1_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASC.2023.3243180"},{"key":"e_1_3_1_88_2","unstructured":"Jaehong Yoon Eunho Yang Jeongtae Lee and Sung Ju Hwang. 2017. Lifelong learning with dynamically expandable networks. arXiv:1708.01547. Retrieved from https:\/\/arxiv.org\/abs\/1708.01547"},{"issue":"11","key":"e_1_3_1_89_2","doi-asserted-by":"crossref","first-page":"12949","DOI":"10.1007\/s10462-023-10464-w","article-title":"A comprehensive review of binary neural network","volume":"56","author":"Yuan Chunyu","year":"2023","unstructured":"Chunyu Yuan and Sos S. Agaian. 2023. A comprehensive review of binary neural network. Artificial Intelligence Review 56, 11 (Nov.2023), 12949\u201313013.","journal-title":"Artificial Intelligence Review"},{"key":"e_1_3_1_90_2","first-page":"12310","volume-title":"International Conference on Machine Learning","author":"Zbontar Jure","year":"2021","unstructured":"Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, and St\u00e9phane Deny. 2021. Barlow twins: Self-supervised learning via redundancy reduction. In International Conference on Machine Learning. PMLR, 12310\u201312320."},{"key":"e_1_3_1_91_2","series-title":"Proceedings of Machine Learning Research","first-page":"3987","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Zenke Friedemann","year":"2017","unstructured":"Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. In Proceedings of the 34th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 70), Doina Precup and Yee Whye Teh (Eds.). PMLR, International Convention Centre, Sydney, Australia, 3987\u20133995."},{"issue":"3","key":"e_1_3_1_92_2","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1109\/JSSC.2022.3218573","article-title":"A 915\u20131220 TOPS\/W, 976\u20131301 GOPS hybrid in-memory computing based always-on image processing for neuromorphic vision sensors","volume":"58","author":"Zhang Xueyong","year":"2023","unstructured":"Xueyong Zhang and Arindam Basu. 2023. A 915\u20131220 TOPS\/W, 976\u20131301 GOPS hybrid in-memory computing based always-on image processing for neuromorphic vision sensors. IEEE Journal of Solid-State Circuits 58, 3 (March2023), 589\u2013599.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"e_1_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3218573"},{"key":"e_1_3_1_94_2","doi-asserted-by":"crossref","first-page":"6848","DOI":"10.1109\/CVPR.2018.00716","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang X.","year":"2018","unstructured":"X. Zhang, X. Zhou, M. Lin, and J. Sun. 2018. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 6848\u20136856. DOI:10.1109\/CVPR.2018.00716"},{"key":"e_1_3_1_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS56072.2025.11043934"},{"key":"e_1_3_1_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429383"},{"key":"e_1_3_1_97_2","first-page":"5867","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhu Fei","year":"2021","unstructured":"Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin, and Cheng-Lin Liu. 2021. Prototype augmentation and self-supervision for incremental learning. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5867\u20135876. DOI:10.1109\/CVPR46437.2021.00581"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3794851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T10:27:57Z","timestamp":1776162477000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3794851"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,14]]},"references-count":96,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3794851"],"URL":"https:\/\/doi.org\/10.1145\/3794851","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,14]]},"assertion":[{"value":"2025-03-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}