{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:25:18Z","timestamp":1755926718498,"version":"3.40.3"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031197772"},{"type":"electronic","value":"9783031197789"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19778-9_18","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:28:41Z","timestamp":1667420921000},"page":"307-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Towards Efficient Adversarial Training on\u00a0Vision Transformers"],"prefix":"10.1007","author":[{"given":"Boxi","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jindong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"18_CR1","unstructured":"Aldahdooh, A., Hamidouche, W., Deforges, O.: Reveal of vision transformers robustness against adversarial attacks. arXiv:2106.03734 (2021)"},{"key":"18_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-030-58592-1_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Andriushchenko","year":"2020","unstructured":"Andriushchenko, M., Croce, F., Flammarion, N., Hein, M.: Square attack: a query-efficient black-box adversarial attack via random search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 484\u2013501. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_29"},{"key":"18_CR3","unstructured":"Andriushchenko, M., Flammarion, N.: Understanding and improving fast adversarial training. In: NeurIPS (2020)"},{"key":"18_CR4","unstructured":"Andriushchenko, M., Flammarion, N.: Understanding and improving fast adversarial training. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, pp. 6\u201312 (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/b8ce47761ed7b3b6f48b583350b7f9e4-Abstract.html"},{"key":"18_CR5","unstructured":"Athalye, A., Carlini, N., Wagner, D.A.: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples. In: ICML. Proceedings of Machine Learning Research, vol. 80, pp. 274\u2013283. PMLR (2018)"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Bai, J., Yuan, L., Xia, S., Yan, S., Li, Z., Liu, W.: Improving vision transformers by revisiting high-frequency components. CoRR abs\/2204.00993 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.00993","DOI":"10.48550\/arXiv.2204.00993"},{"key":"18_CR7","unstructured":"Bai, Y., Mei, J., Yuille, A., Xie, C.: Are transformers more robust than CNNs? arXiv:2111.05464 (2021)"},{"key":"18_CR8","unstructured":"Bai, Y., Mei, J., Yuille, A., Xie, C.: Are transformers more robust than CNNs? In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=hbHkvGBZB9"},{"key":"18_CR9","unstructured":"Benz, P., Ham, S., Zhang, C., Karjauv, A., Kweon, I.S.: Adversarial robustness comparison of vision transformer and MLP-mixer to CNNs. CoRR abs\/2110.02797 (2021). https:\/\/arxiv.org\/abs\/2110.02797"},{"key":"18_CR10","unstructured":"Benz, P., Ham, S., Zhang, C., Karjauv, A., Kweon, I.S.: Adversarial robustness comparison of vision transformer and MLP-mixer to CNNs. arXiv preprint arXiv:2110.02797 (2021)"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Bhojanapalli, S., Chakrabarti, A., Glasner, D., Li, D., Unterthiner, T., Veit, A.: Understanding robustness of transformers for image classification. CoRR abs\/2103.14586 (2021). https:\/\/arxiv.org\/abs\/2103.14586","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Bhojanapalli, S., Chakrabarti, A., Glasner, D., Li, D., Unterthiner, T., Veit, A.: Understanding robustness of transformers for image classification. arXiv:2103.14586 (2021)","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"18_CR13","unstructured":"Brown, T.B., et.al.: Language models are few-shot learners. In: Neural Information Processing Systems, NeurIPS (2020)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.A.: Towards evaluating the robustness of neural networks. In: SP, pp. 39\u201357. IEEE Computer Society (2017)","DOI":"10.1109\/SP.2017.49"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 9630\u20139640. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00951","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"18_CR16","unstructured":"Chen, T., Cheng, Y., Gan, Z., Yuan, L., Zhang, L., Wang, Z.: Chasing sparsity in vision transformers: an end-to-end exploration. CoRR abs\/2106.04533 (2021). https:\/\/arxiv.org\/abs\/2106.04533"},{"key":"18_CR17","unstructured":"Chu, X., et al.: Twins: revisiting spatial attention design in vision transformers. CoRR abs\/2104.13840 (2021)"},{"key":"18_CR18","unstructured":"Croce, F., Hein, M.: Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: ICML (2020)"},{"key":"18_CR19","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics, NAACL, pp. 4171\u20134186 (2019)"},{"key":"18_CR20","unstructured":"Dhillon, G.S., et.al.: Stochastic activation pruning for robust adversarial defense. In: ICLR (2018)"},{"key":"18_CR21","unstructured":"Dosovitskiy, A., et.al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations, ICLR (2021)"},{"key":"18_CR22","unstructured":"Fu, Y., Zhang, S., Wu, S., Wan, C., Lin, Y.: Patch-fool: are vision transformers always robust against adversarial perturbations? In: International Conference on Learning Representations (2022)"},{"key":"18_CR23","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2015). https:\/\/arxiv.org\/abs\/1412.6572"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., J\u00e9gou, H., Douze, M.: LeViT: a vision transformer in convnet\u2019s clothing for faster inference. CoRR abs\/2104.01136 (2021). https:\/\/arxiv.org\/abs\/2104.01136","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"18_CR25","unstructured":"Gu, J., Tresp, V., Qin, Y.: Are vision transformers robust to patch perturbations? CoRR abs\/2111.10659 (2021). https:\/\/arxiv.org\/abs\/2111.10659"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Gu, J., Tresp, V., Qin, Y.: Are vision transformers robust to patch perturbations? In: arXiv preprint arXiv:2111.10659 (2021)","DOI":"10.1007\/978-3-031-19775-8_24"},{"key":"18_CR27","unstructured":"Guo, C., Rana, M., Cisse, M., Van Der Maaten, L.: Countering adversarial images using input transformations. In: ICLR (2018)"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90, https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR29","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1109\/LSP.2021.3112099","volume":"28","author":"H Hu","year":"2021","unstructured":"Hu, H., Lu, X., Zhang, X., Zhang, T., Sun, G.: Inheritance attention matrix-based universal adversarial perturbations on vision transformers. IEEE Signal Process. Lett. 28, 1923\u20131927 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Jia, X., Zhang, Y., Wu, B., Ma, K., Wang, J., Cao, X.: LAS-AT: adversarial training with learnable attack strategy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13398\u201313408, June 2022","DOI":"10.1109\/CVPR52688.2022.01304"},{"key":"18_CR31","doi-asserted-by":"publisher","first-page":"4417","DOI":"10.1109\/TIP.2022.3184255","volume":"31","author":"X Jia","year":"2022","unstructured":"Jia, X., Zhang, Y., Wu, B., Wang, J., Cao, X.: Boosting fast adversarial training with learnable adversarial initialization. IEEE Trans. Image Process. 31, 4417\u20134430 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"18_CR32","unstructured":"Joshi, A., Jagatap, G., Hegde, C.: Adversarial token attacks on vision transformers. arXiv:2110.04337 (2021)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Kim, H., Lee, W., Lee, J.: Understanding catastrophic overfitting in single-step adversarial training. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2\u20139 February 2021, pp. 8119\u20138127. AAAI Press (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16989","DOI":"10.1609\/aaai.v35i9.16989"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Kim, H., Lee, W., Lee, J.: Understanding catastrophic overfitting in single-step adversarial training. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2\u20139 February 2021, pp. 8119\u20138127. AAAI Press (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16989","DOI":"10.1609\/aaai.v35i9.16989"},{"key":"18_CR35","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May, pp. 7\u20139 (2015) Conference Track Proceedings (2015). https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"18_CR36","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"key":"18_CR37","unstructured":"LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). https:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"18_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-030-58574-7_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Liang","year":"2020","unstructured":"Liang, S., Wei, X., Yao, S., Cao, X.: Efficient adversarial attacks for visual object tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 34\u201350. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_3"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Liang, S., Wu, B., Fan, Y., Wei, X., Cao, X.: Parallel rectangle flip attack: a query-based black-box attack against object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7697\u20137707 (2021)","DOI":"10.1109\/ICCV48922.2021.00760"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., Zhu, J.: Defense against adversarial attacks using high-level representation guided denoiser. In: CVPR, pp. 1778\u20131787 (2018)","DOI":"10.1109\/CVPR.2018.00191"},{"key":"18_CR41","doi-asserted-by":"publisher","unstructured":"Liu, W., Jiang, Y., Luo, J., Chang, S.: Noise resistant graph ranking for improved web image search. In: The 24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20\u201325 June 2011, pp. 849\u2013856. IEEE Computer Society (2011). https:\/\/doi.org\/10.1109\/CVPR.2011.5995315, https:\/\/doi.org\/10.1109\/CVPR.2011.5995315","DOI":"10.1109\/CVPR.2011.5995315"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Z., et.al.: Swin transformer: hierarchical vision transformer using shifted windows. CoRR abs\/2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR43","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=rJzIBfZAb"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Mahmood, K., Mahmood, R., Van Dijk, M.: On the robustness of vision transformers to adversarial examples. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7838\u20137847 (2021)","DOI":"10.1109\/ICCV48922.2021.00774"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Mao, X., et al.: Towards robust vision transformer. arXiv:2105.07926 (2021)","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Mao, X., et al.: Rethinking the design principles of robust vision transformer. arXiv:2105.07926 (2021)","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, H.: MagNet: a two-pronged defense against adversarial examples. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 135\u2013147 (2017)","DOI":"10.1145\/3133956.3134057"},{"key":"18_CR48","unstructured":"Mu, N., Wagner, D.: Defending against adversarial patches with robust self-attention. In: ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning (2021)"},{"key":"18_CR49","unstructured":"Naseer, M.M., Ranasinghe, K., Khan, S.H., Hayat, M., Shahbaz Khan, F., Yang, M.H.: Intriguing properties of vision transformers. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"18_CR50","unstructured":"Pan, B., Jiang, Y., Panda, R., Wang, Z., Feris, R., Oliva, A.: IA-RED$${}^{2}$$: interpretability-aware redundancy reduction for vision transformers. CoRR abs\/2106.12620 (2021). https:\/\/arxiv.org\/abs\/2106.12620"},{"key":"18_CR51","doi-asserted-by":"crossref","unstructured":"Park, G.Y., Lee, S.W.: Reliably fast adversarial training via latent adversarial perturbation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00766"},{"key":"18_CR52","unstructured":"Paul, S., Chen, P.: Vision transformers are robust learners. CoRR abs\/2105.07581 (2021). https:\/\/arxiv.org\/abs\/2105.07581"},{"key":"18_CR53","unstructured":"Paul, S., Chen, P.Y.: Vision transformers are robust learners. arXiv:2105.07581 (2021)"},{"key":"18_CR54","unstructured":"Qin, C., et.al.: Adversarial robustness through local linearization. In: NeurIPS (2019)"},{"key":"18_CR55","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.: DynamicViT: efficient vision transformers with dynamic token sparsification. CoRR abs\/2106.02034 (2021). https:\/\/arxiv.org\/abs\/2106.02034"},{"key":"18_CR56","unstructured":"Rice, L., Wong, E., Kolter, J.Z.: Overfitting in adversarially robust deep learning. CoRR abs\/2002.11569 (2020). https:\/\/arxiv.org\/abs\/2002.11569"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et.al.: ImageNet large scale visual recognition challenge (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"18_CR58","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision. IJCV 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision. IJCV"},{"key":"18_CR59","doi-asserted-by":"publisher","unstructured":"S., V.B., Babu, R.V.: Single-step adversarial training with dropout scheduling. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319, 2020, pp. 947\u2013956. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00103. https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/B.S._Single-Step_Adversarial_Training_With_Dropout_Scheduling_CVPR_2020_paper.html","DOI":"10.1109\/CVPR42600.2020.00103"},{"key":"18_CR60","doi-asserted-by":"crossref","unstructured":"Salman, H., Jain, S., Wong, E., Madry, A.: Certified patch robustness via smoothed vision transformers. arXiv:2110.07719 (2021)","DOI":"10.1109\/CVPR52688.2022.01471"},{"key":"18_CR61","unstructured":"Samangouei, P., Kabkab, M., Chellappa, R.: Defense-GAN: protecting classifiers against adversarial attacks using generative models. In: ICLR (2018)"},{"key":"18_CR62","unstructured":"Shafahi, A., et al.: Adversarial training for free! In: NeurIPS (2019)"},{"key":"18_CR63","unstructured":"Shao, R., Shi, Z., Yi, J., Chen, P.Y., Hsieh, C.J.: On the adversarial robustness of visual transformers. arXiv:2103.15670 (2021)"},{"key":"18_CR64","unstructured":"Shi, Y., Han, Y.: Decision-based black-box attack against vision transformers via patch-wise adversarial removal. arXiv preprint arXiv:2112.03492 (2021)"},{"key":"18_CR65","unstructured":"Song, Y., Kim, T., Nowozin, S., Ermon, S., Kushman, N.: PixelDefend: leveraging generative models to understand and defend against adversarial examples. In: ICLR (2018)"},{"key":"18_CR66","unstructured":"Sriramanan, G., et al.: Towards efficient and effective adversarial training. In: NeurIPS (2021)"},{"key":"18_CR67","unstructured":"Szegedy, C., et al.: Intriguing properties of neural networks. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2014). https:\/\/arxiv.org\/abs\/1312.6199"},{"key":"18_CR68","unstructured":"Tang, S., et al.: RobustART: benchmarking robustness on architecture design and training techniques. arXiv preprint arXiv:2109.05211 (2021)"},{"key":"18_CR69","unstructured":"Tang, S., et al.: RobustART: benchmarking robustness on architecture design and training techniques. arXiv preprint arXiv:2109.05211 (2021)"},{"key":"18_CR70","unstructured":"Tang, Y., et.al.: Patch slimming for efficient vision transformers. CoRR abs\/2106.02852 (2021). https:\/\/arxiv.org\/abs\/2106.02852"},{"key":"18_CR71","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, ICML, vol. 139, pp. 10347\u201310357 (2021)"},{"key":"18_CR72","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 139, pp. 10347\u201310357. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"18_CR73","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. CoRR abs\/2103.17239 (2021). https:\/\/arxiv.org\/abs\/2103.17239","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"18_CR74","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems, NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"18_CR75","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u20133 May 2018, Conference Track Proceedings. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"18_CR76","doi-asserted-by":"crossref","unstructured":"Vivek, B., Babu, R.V.: Single-step adversarial training with dropout scheduling. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00103"},{"key":"18_CR77","doi-asserted-by":"crossref","unstructured":"Wang, W., et.al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. CoRR abs\/2102.12122 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"18_CR78","unstructured":"Wang, W., et.al.: Crossformer: a versatile vision transformer hinging on cross-scale attention. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=_PHymLIxuI"},{"key":"18_CR79","unstructured":"Wang, Z., Jiang, W., Zhu, Y., Yuan, L., Song, Y., Liu, W.: DynaMixer: a vision MLP architecture with dynamic mixing. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesv\u00e1ri, C., Niu, G., Sabato, S. (eds.) International Conference on Machine Learning, ICML 2022, 17\u201323 July 2022, Baltimore, Maryland, USA. Proceedings of Machine Learning Research, vol. 162, pp. 22691\u201322701. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/wang22i.html"},{"key":"18_CR80","doi-asserted-by":"crossref","unstructured":"Wei, X., Liang, S., Chen, N., Cao, X.: Transferable adversarial attacks for image and video object detection. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 954\u2013960 (2019)","DOI":"10.24963\/ijcai.2019\/134"},{"key":"18_CR81","unstructured":"Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: revisiting adversarial training. CoRR abs\/2001.03994 (2020). https:\/\/arxiv.org\/abs\/2001.03994"},{"key":"18_CR82","unstructured":"Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A.: Mitigating adversarial effects through randomization. In: ICLR (2018)"},{"key":"18_CR83","unstructured":"Xu, Y., et.al.: Evo-ViT: slow-fast token evolution for dynamic vision transformer. CoRR abs\/2108.01390 (2021). https:\/\/arxiv.org\/abs\/2108.01390"},{"key":"18_CR84","doi-asserted-by":"crossref","unstructured":"Yu, Z., Fu, Y., Li, S., Li, C., Lin, Y.: MIA-former: efficient and robust vision transformers via multi-grained input-adaptation. arXiv preprint arXiv:2112.11542 (2021)","DOI":"10.1609\/aaai.v36i8.20879"},{"key":"18_CR85","unstructured":"Zhang, Q., Yang, Y.: ResT: an efficient transformer for visual recognition. CoRR abs\/2105.13677 (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19778-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:57:36Z","timestamp":1667422656000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19778-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197772","9783031197789"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19778-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}