{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:40:03Z","timestamp":1759333203338,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781711"},{"type":"electronic","value":"9783031781728"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78172-8_3","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:47:04Z","timestamp":1733132824000},"page":"32-45","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Evolutionary Search-Based Operator Fusion Method with\u00a0Binary Representation for\u00a0Deep Learning Inference Acceleration"],"prefix":"10.1007","author":[{"given":"Yu","family":"Yang","sequence":"first","affiliation":[]},{"given":"Boyu","family":"Diao","sequence":"additional","affiliation":[]},{"given":"Hangda","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qiyun","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yongjun","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"3_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.: Yolov4: optimal speed and accuracy of object detection. Cornell University - arXiv, Cornell University - arXiv, April 2020"},{"issue":"1","key":"3_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3520142","volume":"22","author":"X Cai","year":"2022","unstructured":"Cai, X., Wang, Y., Zhang, L.: Optimus: an operator fusion framework for deep neural networks. ACM Trans. Embed. Comput. Syst. 22(1), 1\u201326 (2022)","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"3_CR3","unstructured":"Chen, T., et\u00a0al.: $$\\{$$TVM$$\\}$$: an automated $$\\{$$End-to-End$$\\}$$ optimizing compiler for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2018), pp. 578\u2013594 (2018)"},{"key":"3_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2023.104811","volume":"185","author":"L Dai","year":"2024","unstructured":"Dai, L., Gong, L., An, Z., Xu, Y., Diao, B.: Sketch-fusion: a gradient compression method with multi-layer fusion for communication-efficient distributed training. J. Parallel Distrib. Comput. 185, 104811 (2024)","journal-title":"J. Parallel Distrib. Comput."},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1093\/comjnl\/bxad086","volume":"67","author":"D Dong","year":"2023","unstructured":"Dong, D., Jiang, H., Diao, B.: AKGF: automatic kernel generation for DNN on CPU-FPGA. Comput. J. 67, 1619\u20131627 (2023)","journal-title":"Comput. J."},{"key":"3_CR6","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":"3_CR7","doi-asserted-by":"crossref","unstructured":"Huang, L., Zeng, Y., Yang, C., An, Z., Diao, B., Xu, Y.: eTag: class-incremental learning with embedding distillation and task-oriented generation. arXiv preprint arXiv:2304.10103 (2023)","DOI":"10.1609\/aaai.v38i11.29153"},{"key":"3_CR8","unstructured":"Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., Keutzer, K.: DenseNet: implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)"},{"key":"3_CR9","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$ 0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)"},{"key":"3_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"issue":"3","key":"3_CR11","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1109\/TPDS.2020.3030548","volume":"32","author":"M Li","year":"2020","unstructured":"Li, M., et al.: The deep learning compiler: a comprehensive survey. IEEE Trans. Parallel Distrib. Syst. 32(3), 708\u2013727 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"3_CR12","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/978-3-031-15931-2_58","volume-title":"ICANN 2022","author":"Q Li","year":"2022","unstructured":"Li, Q., Zhang, Z., Diao, B., Xu, Y., Li, C.: Towards understanding the effect of node features on the predictions of graph neural networks. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds.) ICANN 2022. LNCS, vol. 13530, pp. 706\u2013718. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15931-2_58"},{"key":"3_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Ma","year":"2018","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 122\u2013138. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_8"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Niu, W., Guan, J., Wang, Y., Agrawal, G., Ren, B.: DNNFusion: accelerating deep neural networks execution with advanced operator fusion. In: Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, pp. 883\u2013898 (2021)","DOI":"10.1145\/3453483.3454083"},{"key":"3_CR15","unstructured":"NVIDIA Corporation: NVIDIA nsight compute. https:\/\/developer.nvidia.com\/nsight-compute. Accessed 07 Apr 2024"},{"key":"3_CR16","unstructured":"NVIDIA Corporation: NVIDIA tesla v100. https:\/\/www.nvidia.com\/en-gb\/data-center\/tesla-v100\/. Accessed 14 Mar 2024"},{"key":"3_CR17","unstructured":"NVIDIA Corporation: NVIDIA Jetson Orin NX card (2023). https:\/\/www.nvidia.cn\/autonomous-machines\/embedded-systems\/jetson-orin\/. Accessed 24 Jan 2024"},{"issue":"8","key":"3_CR18","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"3_CR19","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":"3_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3_CR21","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks"},{"key":"3_CR22","unstructured":"Turc, I., Chang, M.W., Lee, K., Toutanova, K.: Well-read students learn better: on the importance of pre-training compact models. arXiv preprint arXiv:1908.08962v2 (2019)"},{"issue":"2","key":"3_CR23","volume":"4","author":"Q Wang","year":"2023","unstructured":"Wang, Q., et al.: How to prevent malicious use of intelligent unmanned swarms? Innov. 4(2), 100396 (2023)","journal-title":"Innov."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Xu, J., Diao, B., Cui, B., Yang, K., Li, C., Hong, H.: Pruning filter via gaussian distribution feature for deep neural networks acceleration. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892389"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Yao, K., Wang, J., Diao, B., Li, C.: Towards understanding the generalization of deepfake detectors from a game-theoretical view. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2031\u20132041 (2023)","DOI":"10.1109\/ICCV51070.2023.00194"},{"key":"3_CR26","first-page":"1","volume":"4","author":"J Zhao","year":"2022","unstructured":"Zhao, J., et al.: Apollo: automatic partition-based operator fusion through layer by layer optimization. Proc. Mach. Learn. Syst. 4, 1\u201319 (2022)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"3_CR27","unstructured":"Zheng, L., et\u00a0al.: Ansor: generating $$\\{$$High-Performance$$\\}$$ tensor programs for deep learning. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2020), pp. 863\u2013879 (2020)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Zheng, Z., et\u00a0al.: AStitch: enabling a new multi-dimensional optimization space for memory-intensive ML training and inference on modern SIMT architectures. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 359\u2013373 (2022)","DOI":"10.1145\/3503222.3507723"},{"key":"3_CR29","unstructured":"Zheng, Z., et al.: FusionStitching: boosting memory intensive computations for deep learning workloads. arXiv preprint arXiv:2009.10924 (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78172-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:04:22Z","timestamp":1733133862000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78172-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031781711","9783031781728"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78172-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}