{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:16:50Z","timestamp":1778080610569,"version":"3.51.4"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s11263-024-02211-7","type":"journal-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T07:02:29Z","timestamp":1727334149000},"page":"1222-1237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Slimmable Networks for Contrastive Self-supervised Learning"],"prefix":"10.1007","volume":"133","author":[{"given":"Shuai","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6206-7911","authenticated-orcid":false,"given":"Xiaohan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"key":"2211_CR1","first-page":"12980","volume":"33","author":"S Abbasi Koohpayegani","year":"2020","unstructured":"Abbasi Koohpayegani, S., Tejankar, A., & Pirsiavash, H. (2020). Compress: Self-supervised learning by compressing representations. NeurIPS, 33, 12980\u201312992.","journal-title":"NeurIPS"},{"issue":"9","key":"2211_CR2","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1109\/TPAMI.2015.2496141","volume":"38","author":"D Alexey","year":"2016","unstructured":"Alexey, D., Fischer, P., Tobias, J., Springenberg, M. R., & Brox, T. (2016). Discriminative unsupervised feature learning with exemplar convolutional neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(9), 1734\u20131747.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2211_CR3","first-page":"15509","volume":"32","author":"P Bachman","year":"2019","unstructured":"Bachman, P., Hjelm, R. D., & Buchwalter, W. (2019). Learning representations by maximizing mutual information across views. NeurIPS, 32, 15509\u201315519.","journal-title":"NeurIPS"},{"key":"2211_CR4","unstructured":"Ballard, D. H. (1987). Modular learning in neural networks. In National conference on artificial intelligence (pp. 279\u2013284)."},{"key":"2211_CR5","unstructured":"Cai, H., Gan, C., Wang, T., Zhang, Z., & Han, S. (2020). Once-for-all: Train one network and specialize it for efficient deployment. In ICLR."},{"key":"2211_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018). Deep clustering for unsupervised learning of visual features. In ECCV (pp. 132\u2013149).","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"2211_CR7","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. NeurIPS, 33, 9912\u20139924.","journal-title":"NeurIPS"},{"key":"2211_CR8","doi-asserted-by":"crossref","unstructured":"Chavan, A., Shen, Z., Liu, Z., Liu, Z., Cheng, K. T., & Xing, E. P. (2022). Vision transformer slimming: Multi-dimension searching in continuous optimization space. In CVPR (pp. 4931\u20134941).","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"2211_CR9","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et\u00a0al. (2019). Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155"},{"key":"2211_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020a). A simple framework for contrastive learning of visual representations. In ICML, PMLR (pp. 1597\u20131607)."},{"key":"2211_CR11","first-page":"22243","volume":"33","author":"T Chen","year":"2020","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., & Hinton, G. E. (2020). Big self-supervised models are strong semi-supervised learners. NeurIPS, 33, 22243\u201322255.","journal-title":"NeurIPS"},{"key":"2211_CR12","unstructured":"Chen, X., Fan, H., Girshick, R., & He, K. (2020c). Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297"},{"key":"2211_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., & He, K. (2021). Exploring simple siamese representation learning. In CVPR (pp. 15750\u201315758).","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2211_CR14","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., & He, K. (2021). An empirical study of training self-supervised vision transformers. In ICCV (pp. 9640\u20139649).","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"2211_CR15","unstructured":"Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT (pp. 4171\u20134186)."},{"key":"2211_CR16","unstructured":"Fang, Z., Wang, J., Wang, L., Zhang, L., Yang, Y., & Liu, Z. (2021). SEED: Self-supervised distillation for visual representation. In ICLR."},{"key":"2211_CR17","doi-asserted-by":"crossref","unstructured":"Gao, Y., Zhuang, J. X., Lin, S., Cheng, H., Sun, X., Li, K., & Shen, C. (2022). Disco: Remedying self-supervised learning on lightweight models with distilled contrastive learning. In ECCV (pp. 237\u2013253). Springer.","DOI":"10.1007\/978-3-031-19809-0_14"},{"key":"2211_CR18","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., & He, K. (2017). Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677"},{"key":"2211_CR19","unstructured":"Gu, J., Liu, W., & Tian, Y. (2021). Simple distillation baselines for improving small self-supervised models. arXiv preprint arXiv:2106.11304"},{"key":"2211_CR20","unstructured":"Guo, J., Chen, M., Hu, Y., Zhu, C., He, X., & Cai, D. (2020). Reducing the teacher\u2013student gap via spherical knowledge disitllation. arXiv preprint arXiv:2010.07485"},{"key":"2211_CR21","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 CVPR (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2211_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In CVPR (pp. 9729\u20139738).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2211_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In ICCV (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2211_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2211_CR25","doi-asserted-by":"crossref","unstructured":"He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (2019). Bag of tricks for image classification with convolutional neural networks. In CVPR (pp. 558\u2013567).","DOI":"10.1109\/CVPR.2019.00065"},{"key":"2211_CR26","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531"},{"key":"2211_CR27","unstructured":"Hjelm, R. D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A., & Bengio, Y. (2019). Learning deep representations by mutual information estimation and maximization. In ICLR."},{"key":"2211_CR28","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, pmlr (pp. 448\u2013456)."},{"key":"2211_CR29","unstructured":"Kingma, D. P., & Welling, M. (2014). Auto-encoding variational bayes. In ICLR."},{"key":"2211_CR30","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al. (2009). Learning multiple layers of features from tiny images."},{"key":"2211_CR31","doi-asserted-by":"crossref","unstructured":"Li, C., Wang, G., Wang, B., Liang, X., Li, Z., & Chang, X. (2021). Dynamic slimmable network. In CVPR (pp. 8607\u20138617).","DOI":"10.1109\/CVPR46437.2021.00850"},{"issue":"4","key":"2211_CR32","doi-asserted-by":"publisher","first-page":"4430","DOI":"10.1109\/TPAMI.2022.3194044","volume":"45","author":"C Li","year":"2022","unstructured":"Li, C., Wang, G., Wang, B., Liang, X., Li, Z., & Chang, X. (2022). Ds-net++: Dynamic weight slicing for efficient inference in cnns and vision transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4430\u20134446.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2211_CR33","first-page":"6391","volume":"31","author":"H Li","year":"2018","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., & Goldstein, T. (2018). Visualizing the loss landscape of neural nets. NeurIPS, 31, 6391\u20136401.","journal-title":"NeurIPS"},{"key":"2211_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In CVPR (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"2211_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In ECCV (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"1","key":"2211_CR36","first-page":"857","volume":"35","author":"X Liu","year":"2021","unstructured":"Liu, X., Zhang, F., Hou, Z., Mian, L., Wang, Z., Zhang, J., & Tang, J. (2021). Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering, 35(1), 857\u2013876.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2211_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., & Zhang, C. (2017). Learning efficient convolutional networks through network slimming. In ICCV (pp. 2736\u20132744).","DOI":"10.1109\/ICCV.2017.298"},{"key":"2211_CR38","unstructured":"Micikevicius, P., Narang, S., Alben, J., Diamos, GF., Elsen, E., Garc\u00eda, D., Ginsburg, B., Houston, M., Kuchaiev, O., Venkatesh, G., & Wu, H. (2018). Mixed precision training. In ICLR."},{"key":"2211_CR39","doi-asserted-by":"publisher","first-page":"5191","DOI":"10.1609\/aaai.v34i04.5963","volume":"34","author":"SI Mirzadeh","year":"2020","unstructured":"Mirzadeh, S. I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., & Ghasemzadeh, H. (2020). Improved knowledge distillation via teacher assistant. AAAI, 34, 5191\u20135198.","journal-title":"AAAI"},{"key":"2211_CR40","unstructured":"NVIDIA. (2021). Nvidia dali: The nvidia data loading library. https:\/\/developer.nvidia.com\/dali"},{"key":"2211_CR41","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., & Cho, M. (2019). Relational knowledge distillation. In CVPR (pp. 3967\u20133976).","DOI":"10.1109\/CVPR.2019.00409"},{"key":"2211_CR42","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016). Context encoders: Feature learning by inpainting. In CVPR (pp. 2536\u20132544).","DOI":"10.1109\/CVPR.2016.278"},{"key":"2211_CR43","doi-asserted-by":"crossref","unstructured":"Peng, B., Jin, X., Liu, J., Li, D., Wu, Y., Liu, Y., Zhou, S., & Zhang, Z. (2019). Correlation congruence for knowledge distillation. In ICCV (pp. 5007\u20135016).","DOI":"10.1109\/ICCV.2019.00511"},{"key":"2211_CR44","unstructured":"Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. In ICLR."},{"key":"2211_CR45","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., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2211_CR46","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1609\/aaai.v36i2.20120","volume":"36","author":"H Shi","year":"2022","unstructured":"Shi, H., Zhang, Y., Tang, S., Zhu, W., Li, Y., Guo, Y., & Zhuang, Y. (2022). On the efficacy of small self-supervised contrastive models without distillation signals. AAAI, 36, 2225\u20132234.","journal-title":"AAAI"},{"key":"2211_CR47","unstructured":"Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In ICML, PMLR (pp. 6105\u20136114)."},{"key":"2211_CR48","unstructured":"Tian, Y., Krishnan, D., & Isola, P. (2020). Contrastive representation distillation. In ICLR."},{"key":"2211_CR49","unstructured":"Tomasev, N., Bica, I., McWilliams, B., Buesing, L., Pascanu, R., Blundell, C., & Mitrovic, J. (2022). Pushing the limits of self-supervised resnets: Can we outperform supervised learning without labels on imagenet? arXiv preprint arXiv:2201.05119"},{"key":"2211_CR50","unstructured":"Van den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et al. (2016a). Conditional image generation with pixelcnn decoders. NeurIPS, 29, 4790\u20134798."},{"key":"2211_CR51","unstructured":"Van Den\u00a0Oord, A., Kalchbrenner, N., & Kavukcuoglu, K. (2016b). Pixel recurrent neural networks. In ICML, PMLR (pp. 1747\u20131756)."},{"key":"2211_CR52","unstructured":"Van\u00a0den Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"2211_CR53","unstructured":"Wang, W., Chen, M., Zhao, S., Chen, L., Hu, J., Liu, H., Cai, D., He, X., & Liu, W. (2021). Accelerate cnns from three dimensions: A comprehensive pruning framework. In ICML, PMLR (pp. 10717\u201310726)."},{"key":"2211_CR54","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S. X., & Lin, D. (2018). Unsupervised feature learning via non-parametric instance discrimination. In CVPR (pp. 3733\u20133742).","DOI":"10.1109\/CVPR.2018.00393"},{"key":"2211_CR55","unstructured":"Xu, H., Fang, J., Zhang, X., Xie, L., Wang, X., Dai, W., Xiong, H., & Tian, Q. (2022). Bag of instances aggregation boosts self-supervised distillation. In ICLR."},{"key":"2211_CR56","doi-asserted-by":"crossref","unstructured":"Yang, T., Zhu, S., Chen, C., Yan, S., Zhang, M., & Willis, A. (2020). Mutualnet: Adaptive convnet via mutual learning from network width and resolution. In ECCV (pp. 299\u2013315).","DOI":"10.1007\/978-3-030-58452-8_18"},{"key":"2211_CR57","unstructured":"You, Y., Gitman, I., & Ginsburg, B. (2017). Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888"},{"key":"2211_CR58","unstructured":"Yu, J., & Huang, T. (2019a). Autoslim: Towards one-shot architecture search for channel numbers. arXiv preprint arXiv:1903.11728"},{"key":"2211_CR59","doi-asserted-by":"crossref","unstructured":"Yu, J., & Huang, T. S. (2019b). Universally slimmable networks and improved training techniques. In ICCV (pp. 1803\u20131811).","DOI":"10.1109\/ICCV.2019.00189"},{"key":"2211_CR60","doi-asserted-by":"crossref","unstructured":"Yu, J., Jin, P., Liu, H., Bender, G., Kindermans, P., Tan, M., Huang, T. S., Song, X., Pang, R., & Le, Q. (2020). Bignas: Scaling up neural architecture search with big single-stage models. In ECCV (pp. 702\u2013717). Springer.","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"2211_CR61","unstructured":"Yu, J., Yang, L., Xu, N., Yang, J., & Huang, T. S. (2019). Slimmable neural networks. In ICLR."},{"key":"2211_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., & Efros, A. A. (2016). Colorful image colorization. In ECCV (pp. 649\u2013666). Springer.","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"2211_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T. M., & Lu, H. (2018). Deep mutual learning. In CVPR (pp. 4320\u20134328).","DOI":"10.1109\/CVPR.2018.00454"},{"key":"2211_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., & Liang, J. (2022a). Decoupled knowledge distillation. In CVPR (pp. 11953\u201311962).","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"2211_CR65","doi-asserted-by":"publisher","first-page":"5869","DOI":"10.1109\/TIP.2022.3201602","volume":"31","author":"S Zhao","year":"2022","unstructured":"Zhao, S., Zhou, L., Wang, W., Cai, D., Lam, T. L., & Xu, Y. (2022). Toward better accuracy-efficiency trade-offs: Divide and co-training. IEEE Transactions on Image Processing, 31, 5869\u20135880.","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02211-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02211-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02211-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T19:31:19Z","timestamp":1740425479000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02211-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,26]]},"references-count":65,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["2211"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02211-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,26]]},"assertion":[{"value":"6 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}