{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T05:02:50Z","timestamp":1785214970443,"version":"3.55.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62372451"],"award-info":[{"award-number":["62372451"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62192785"],"award-info":[{"award-number":["62192785"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["M22005"],"award-info":[{"award-number":["M22005"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62372082"],"award-info":[{"award-number":["62372082"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272125"],"award-info":[{"award-number":["62272125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62306312"],"award-info":[{"award-number":["62306312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62036011"],"award-info":[{"award-number":["62036011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62192782"],"award-info":[{"award-number":["62192782"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U1936204"],"award-info":[{"award-number":["U1936204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11263-024-02002-0","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T12:02:28Z","timestamp":1708344148000},"page":"2798-2824","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Cross-Architecture Knowledge Distillation"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8426-9335","authenticated-orcid":false,"given":"Yufan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajiong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5888-6735","authenticated-orcid":false,"given":"Bing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingting","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Maybank","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,19]]},"reference":[{"key":"2002_CR1","doi-asserted-by":"crossref","unstructured":"Aguilar, G., Ling, Y., Zhang, Y., Yao, B., Fan, X., & Guo, C. (2020). Knowledge distillation from internal representations. In: Proceedings of the AAAI conference on artificial intelligence (Vol. 34, pp. 7350\u20137357).","DOI":"10.1609\/aaai.v34i05.6229"},{"key":"2002_CR2","unstructured":"Ba, J., & Caruana, R. (2014). Do deep nets really need to be deep? Advances in Neural Information Processing Systems, 27, 2654\u20132662."},{"key":"2002_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In: Proceedings of the european conference on computer vision (pp. 213\u2013229).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2002_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., & He, K. (2021). Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 15750\u201315758).","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2002_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In: International conference on machine learning (pp. 1597\u2013 1607)."},{"key":"2002_CR6","doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, S., Zhao, H., Jia, J. (2021). Distilling knowledge via knowledge review. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5008\u20135017).","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"2002_CR7","unstructured":"Cheng, Y., Wang, D., Zhou, P., Zhang, T. (2017). A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282."},{"key":"2002_CR8","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1251\u20131258).","DOI":"10.1109\/CVPR.2017.195"},{"key":"2002_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., . . . others (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929."},{"key":"2002_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R. (2022). Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2002_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R. (2017). Mask r-cnn. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2002_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2002_CR13","doi-asserted-by":"crossref","unstructured":"Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y. (2019). A comprehensive overhaul of feature distillation. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1921\u20131930).","DOI":"10.1109\/ICCV.2019.00201"},{"key":"2002_CR14","doi-asserted-by":"crossref","unstructured":"Heo, B., Lee, M., Yun, S., Choi, J.Y. (2019). Knowledge transfer via distillation of activation boundaries formed by hidden neurons. In: Proceedings of the AAAI conference on artificial intelligence (Vol. 33, pp. 3779\u20133787).","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"2002_CR15","unstructured":"Hinton, G., Vinyals, O., Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531."},{"key":"2002_CR16","unstructured":"Huang, Z., & Wang, N. (2017). Like what you like: Knowledge distill via neuron selectivity transfer. arXiv preprint arXiv:1707.01219."},{"key":"2002_CR17","first-page":"1","volume":"31","author":"J Kim","year":"2018","unstructured":"Kim, J., Park, S., & Kwak, N. (2018). Paraphrasing complex network: Network compression via factor transfer. Advances in neural information processing systems, 31, 1\u201310.","journal-title":"Advances in neural information processing systems"},{"key":"2002_CR18","unstructured":"Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images."},{"key":"2002_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L. (2014). Microsoft coco: Common objects in context. In: Proceedings of the European conference on computer vision (pp. 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2002_CR20","doi-asserted-by":"crossref","unstructured":"Lin, S., Xie, H., Wang, B., Yu, K., Chang, X., Liang, X., Wang, G. (2022). Knowledge distillation via the target-aware transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10915\u201310924).","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"2002_CR21","unstructured":"Liu, Y., Cao, J., Li, B., Hu,W., Ding, J., Li, L. (2022). Cross-architecture knowledge distillation. In: Proceedings of the Asian conference on computer vision (pp. 3396\u20133411)."},{"key":"2002_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cao, J., Li, B., Yuan, C., Hu, W., Li, Y., Duan, Y. (2019). Knowledge distillation via instance relationship graph. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7096\u20137104).","DOI":"10.1109\/CVPR.2019.00726"},{"key":"2002_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J. (2019). Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2604\u20132613).","DOI":"10.1109\/CVPR.2019.00271"},{"key":"2002_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H.,Wei, Y., Zhang, Z., Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2002_CR25","unstructured":"Nvidia (2007, Jun). Cuda. https:\/\/developer.nvidia.com\/cuda-zone. Author."},{"key":"2002_CR26","unstructured":"Nvidia (2022). Tensorrt. https:\/\/developer.nvidia.com\/tensorrt. Author."},{"key":"2002_CR27","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M. (2019). Relational knowledge distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3967\u20133976).","DOI":"10.1109\/CVPR.2019.00409"},{"key":"2002_CR28","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lerer, A. (n.d.). Automatic differentiation in pytorch. In: Advances in neural information processing systems workshop (pp. 1\u20134)."},{"key":"2002_CR29","doi-asserted-by":"crossref","unstructured":"Ren, S., Gao, Z., Hua, T., Xue, Z., Tian, Y., He, S., Zhao, H. (2022). Co-advise: Cross inductive bias distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16773\u201316782).","DOI":"10.1109\/CVPR52688.2022.01627"},{"key":"2002_CR30","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, 91\u201399.","journal-title":"Advances in neural information processing systems"},{"key":"2002_CR31","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y. (2014). Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550."},{"issue":"3","key":"2002_CR32","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., & Fei-Fei, L. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2002_CR33","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4510\u20134520).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2002_CR34","doi-asserted-by":"crossref","unstructured":"Shang, Y., Duan, B., Zong, Z., Nie, L., Yan, Y. (2021). Lipschitz continuity guided knowledge distillation. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10675\u201310684).","DOI":"10.1109\/ICCV48922.2021.01050"},{"key":"2002_CR35","doi-asserted-by":"crossref","unstructured":"Song, J., Zhang, H.,Wang, X., Xue, M., Chen, Y., Sun, L., Song, M. (2021). Tree-like decision distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13488\u201313497).","DOI":"10.1109\/CVPR46437.2021.01328"},{"key":"2002_CR36","doi-asserted-by":"publisher","first-page":"3359","DOI":"10.1109\/TIP.2022.3170728","volume":"31","author":"J Song","year":"2022","unstructured":"Song, J., Chen, Y., Ye, J., & Song, M. (2022). Spotadaptive knowledge distillation. IEEE Transactions on Image Processing, 31, 3359\u20133370.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2002_CR37","unstructured":"Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning (pp. 6105\u20136114)."},{"key":"2002_CR38","doi-asserted-by":"crossref","unstructured":"Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C. (2018). A survey on deep transfer learning. In: International conference on artificial neural networks (pp. 270\u2013279).","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"2002_CR39","unstructured":"Tencent (2017). Ncnn. https:\/\/github.com\/tencent\/ncnn. Author."},{"key":"2002_CR40","unstructured":"Tian, Y., Krishnan, D., Isola, P. (2019). Contrastive representation distillation. arXiv preprint arXiv:1910.10699."},{"key":"2002_CR41","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H. (2021). Training data-efficient image transformers & distillation through attention. In: International conference on machine learning (pp. 10347\u201310357)."},{"key":"2002_CR42","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Polosukhin, I. (2017). Attention is all you need. In: Advances in neural information processing systems (pp. 5998\u20136008)."},{"key":"2002_CR43","unstructured":"Wang, K., Gao, X., Zhao, Y., Li, X., Dou, D., Xu, C.- Z. (2019). Pay attention to features, transfer learn faster CNNS. In: International conference on learning representations (pp. 1\u201314)."},{"key":"2002_CR44","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M. (2020). Minilm: Deep selfattention distillation for task-agnostic compression of pre-trained transformers. arXiv preprint arXiv:2002.10957."},{"key":"2002_CR45","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J. (2017). A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4133\u20134141).","DOI":"10.1109\/CVPR.2017.754"},{"key":"2002_CR46","unstructured":"Zagoruyko, S., & Komodakis, N. (2016). Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928."},{"key":"2002_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yin, Z., Li, Y., Yin, G., Yan, J., Shao, J., Liu, Z. (2020). Celeba-spoof: Large-scale face anti-spoofing dataset with rich annotations. In: Proceedings of the European conference on computer vision (pp. 70\u201385)","DOI":"10.1007\/978-3-030-58610-2_5"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02002-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02002-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02002-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T14:09:59Z","timestamp":1720706999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02002-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,19]]},"references-count":47,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["2002"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02002-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,19]]},"assertion":[{"value":"20 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}