{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:27:55Z","timestamp":1757618875819,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819697939"},{"type":"electronic","value":"9789819697946"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-9794-6_29","type":"book-chapter","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T06:13:09Z","timestamp":1752473589000},"page":"346-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DEVR: Train an Efficient Vision-RWKV Model with Improved Knowledge Distillation"],"prefix":"10.1007","author":[{"given":"Xuhong","family":"Li","sequence":"first","affiliation":[]},{"given":"Limin","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Jianjun","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR2","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"29_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE (2009), pp. 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR5","unstructured":"Park, N., Kim, S.K.: How do vision transformers work? In: 10th International Conference on Learning Representations, ICLR 2022 (2022)"},{"key":"29_CR6","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"29_CR7","unstructured":"Peng, B., et al.: RWKV: Reinventing RNNs for the transformer era. arXiv preprint arXiv:2305.13048 (2023)"},{"key":"29_CR8","unstructured":"Duan, Y.C., et al.: Vision-RWKV: efficient and scalable visual perception with RWKV-like architectures. arXiv preprint arXiv:2403.02308 (2024)"},{"key":"29_CR9","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H.Z., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.N.: A ConvNet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022), pp. 11976\u201311986","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"29_CR11","unstructured":"Bahdanau, D., Cho, K.H., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"29_CR12","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 (2021), pp. 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"29_CR13","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. PMLR (2021), pp. 10347\u201310357"},{"key":"29_CR14","unstructured":"Sun, Y.T., et al.: Retentive network: a successor to transformer for large language models. arXiv preprint arXiv:2307.08621 (2023)"},{"key":"29_CR15","unstructured":"Zhu, L.H., Liao, B.C., Zhang, Q., Wang, X.L., Liu, W.Y., Wang, X.G.: Vision Mamba: efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"},{"issue":"10","key":"29_CR16","doi-asserted-by":"publisher","first-page":"12581","DOI":"10.1109\/TPAMI.2023.3282631","volume":"45","author":"KC Li","year":"2023","unstructured":"Li, K.C., et al.: Uniformer: unifying convolution and self-attention for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12581\u201312600 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Ren, S.C., Yang, X.Y., Liu, S.H., Wang, X.C.: SGFormer: self-guided transformer with evolving token reallocation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023), pp. 6003\u20136014","DOI":"10.1109\/ICCV51070.2023.00552"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Lin, W.F., Wu, Z.H., Chen, J.Y., Huang, J., Jin, L.W.: Scale-aware modulation meet transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023), pp. 6015\u20136026","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Kautz, J.: MambaVision: a hybrid mamba transformer vision backbone. arXiv preprint arXiv:2407.08083 (2024)","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"29_CR20","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"29_CR21","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"key":"29_CR22","unstructured":"Tian, Y.L., Krishnan, D., Isola, P.: Contrastive representation distillation. In: International Conference on Learning Representations (2020)"},{"key":"29_CR23","unstructured":"Liu, D.Y., Kan, M.N., Shan, S.G., Chen, X.L.: Function consistent feature distillation. arXiv preprint arXiv:2304.11832 (2023)"},{"key":"29_CR24","unstructured":"Hao, Z.W., et al.: One-for-All: bridge the gap between heterogeneous architectures in knowledge distillation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"29_CR25","unstructured":"Yuan, L., Tay, F.E.H., Li, G.L., Wang, T., Feng, J.S.: Revisit Knowledge Distillation: A Teacher-Free Framework (2019)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"He, K.M., Fan, H.Q., Wu, Y.X., Xie, S.N., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"29_CR27","unstructured":"Loshchilov, I.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"He, K.M., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (2017), pp. 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"29_CR29","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534 (2022)"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Xiao, T.T., Liu, Y.C., Zhou, B.L., Jiang, Y.N., Sun, J.: Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 418\u2013434","DOI":"10.1007\/978-3-030-01228-1_26"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9794-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T07:59:24Z","timestamp":1757231964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9794-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819697939","9789819697946"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9794-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}