{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:38:37Z","timestamp":1763552317735,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620630"},{"type":"electronic","value":"9789819620647"}],"license":[{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"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\/978-981-96-2064-7_23","type":"book-chapter","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:24:39Z","timestamp":1735327479000},"page":"311-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["RobSparse: Automatic Search for\u00a0GPU-Friendly Robust and\u00a0Sparse Vision Transformers"],"prefix":"10.1007","author":[{"given":"Yulan","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sisi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingbin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lutan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, S., Hu, S.X., Damianou, A., Lawrence, N.D., Dai, Z.: Variational information distillation for knowledge transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9163\u20139171 (2019)","DOI":"10.1109\/CVPR.2019.00938"},{"key":"23_CR2","unstructured":"Bai, Y., Mei, J., Yuille, A.L., Xie, C.: Are transformers more robust than CNNS? In: Advances in Neural Information Processing Systems, vol. 34, pp. 26831\u201326843 (2021)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Cao, J., et al.: MadTP: multimodal alignment-guided dynamic token pruning for accelerating vision-language transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15710\u201315719 (2024)","DOI":"10.1109\/CVPR52733.2024.01487"},{"key":"23_CR4","unstructured":"Chen, T., Cheng, Y., Gan, Z., Yuan, L., Zhang, L., Wang, Z.: Chasing sparsity in vision transformers: an end-to-end exploration. In: Advances in Neural Information Processing Systems, vol. 34, pp. 19974\u201319988 (2021)"},{"key":"23_CR5","unstructured":"Croce, F., Hein, M.: Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: International Conference on Machine Learning, pp. 2206\u20132216. PMLR (2020)"},{"key":"23_CR6","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., Sagun, L.: ConViT: improving vision transformers with soft convolutional inductive biases. In: International Conference on Machine Learning, pp. 2286\u20132296. PMLR (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"23_CR8","unstructured":"Francesco\u00a0Croce, M.A., Vikash\u00a0Sehwag, E.D.: Robustbench. https:\/\/robustbench.github.io\/"},{"key":"23_CR9","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"23_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/11564089_7","volume-title":"Algorithmic Learning Theory","author":"A Gretton","year":"2005","unstructured":"Gretton, A., Bousquet, O., Smola, A., Sch\u00f6lkopf, B.: Measuring statistical dependence with Hilbert-Schmidt norms. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 63\u201377. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11564089_7"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Jain, S., Dutta, T.: Towards understanding and improving adversarial robustness of vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24736\u201324745 (2024)","DOI":"10.1109\/CVPR52733.2024.02336"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Jian, T., Wang, Z., Wang, Y., Dy, J., Ioannidis, S.: Pruning adversarially robust neural networks without adversarial examples. In: 2022 IEEE International Conference on Data Mining (ICDM), pp. 993\u2013998. IEEE (2022)","DOI":"10.1109\/ICDM54844.2022.00120"},{"key":"23_CR13","unstructured":"Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR15","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"23_CR16","unstructured":"Mishra, A., et al.: Accelerating sparse deep neural networks. arXiv preprint arXiv:2104.08378 (2021)"},{"key":"23_CR17","unstructured":"Mo, Y., Wu, D., Wang, Y., Guo, Y., Wang, Y.: When adversarial training meets vision transformers: recipes from training to architecture. In: Advances in Neural Information Processing Systems, vol. 35, pp. 18599\u201318611 (2022)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 377\u2013386 (2021)","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"23_CR19","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: Advances in Neural Information Processing Systems, vol. 34, pp. 13937\u201313949 (2021)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Patch slimming for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12165\u201312174 (2022)","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"23_CR21","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. arXiv preprint physics\/0004057 (2000)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: 2015 IEEE Information Theory Workshop (ITW), pp.\u00a01\u20135. IEEE (2015)","DOI":"10.1109\/ITW.2015.7133169"},{"key":"23_CR23","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Ye, H., et al.: Once for both: single stage of importance and sparsity search for vision transformer compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5578\u20135588 (2024)","DOI":"10.1109\/CVPR52733.2024.00533"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Yu, F., Huang, K., Wang, M., Cheng, Y., Chu, W., Cui, L.: Width & depth pruning for vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3143\u20133151 (2022)","DOI":"10.1609\/aaai.v36i3.20222"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Yu, L., Xiang, W.: X-pruner: explainable pruning for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24355\u201324363 (2023)","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"23_CR27","unstructured":"Yu, S., et al.: Unified visual transformer compression. arXiv preprint arXiv:2203.08243 (2022)"},{"key":"23_CR28","unstructured":"Zhang, Q., et al.: Platon: pruning large transformer models with upper confidence bound of weight importance. In: International Conference on Machine Learning, pp. 26809\u201326823. PMLR (2022)"},{"key":"23_CR29","unstructured":"Zhang, Y., Wei, L., Freris, N.: Synergistic patch pruning for vision transformer: unifying intra- & inter-layer patch importance. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"23_CR30","unstructured":"Zhu, M., Tang, Y., Han, K.: Vision transformer pruning. arXiv preprint arXiv:2104.08500 (2021)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2064-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T20:04:47Z","timestamp":1735329887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2064-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,28]]},"ISBN":["9789819620630","9789819620647"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2064-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,28]]},"assertion":[{"value":"28 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}