{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T04:52:58Z","timestamp":1780807978439,"version":"3.54.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Education Department of Shaanxi Provincial Governmen","award":["23JK0450"],"award-info":[{"award-number":["23JK0450"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00371-025-04236-6","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:28:15Z","timestamp":1765477695000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing low-rank decomposition for efficient attention-based vision models via adaptive neural architecture search"],"prefix":"10.1007","volume":"42","author":[{"given":"Yao","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"key":"4236_CR1","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arxiv preprint arXiv:2010.11929 (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"4236_CR2","first-page":"24101","volume":"35","author":"W Kwon","year":"2022","unstructured":"Kwon, W., Kim, S., Mahoney, M.W.: A fast post-training pruning framework for transformers. Adv. Neural. Inf. Process. Syst. 35, 24101\u201324116 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4236_CR3","doi-asserted-by":"publisher","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arxiv preprint arXiv:1503.02531(2015). https:\/\/doi.org\/10.48550\/arxiv.1503.02531","DOI":"10.48550\/arxiv.1503.02531"},{"key":"4236_CR4","doi-asserted-by":"publisher","unstructured":"Phan, A.H., Sobolev, K., Sozykin, K.: Stable low-rank tensor decomposition for compression of convolutional neural network. Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIX 16. pp 522\u2013539 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_31","DOI":"10.1007\/978-3-030-58526-6_31"},{"key":"4236_CR5","doi-asserted-by":"publisher","unstructured":"Fan, X., Liu, Z., Lian, J.: Lighter and better: low-rank decomposed self-attention networks for next-item recommendation. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1733\u20131737 (2021). https:\/\/doi.org\/10.1145\/3404835.3462978","DOI":"10.1145\/3404835.3462978"},{"issue":"11","key":"4236_CR6","doi-asserted-by":"publisher","first-page":"13489","DOI":"10.1109\/TPAMI.2023.3293885","volume":"45","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Qiu, G., Li, P., Zhu, L., Yang, X., Sheng, B.: Mngnas: distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13489\u201313508 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3293885","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4236_CR7","unstructured":"Liu, H., Simonyan, K., Yang, Y.,: Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018). https:\/\/arxiv.org\/abs\/1806.09055v1"},{"key":"4236_CR8","doi-asserted-by":"crossref","unstructured":"Chen. X., Xie, L., Wu, J.: Progressive differentiable architecture search: Bridging the depth gap between search and evaluation. Proceedings of the IEEE\/CVF International Conference on Computer Vision. [S.l.]: IEEE, 2019: 1294\u20131303 (2019)","DOI":"10.1109\/ICCV.2019.00138"},{"key":"4236_CR9","unstructured":"Xu, Y., Xie, L., Zhang, X.: PC-DARTS: Partial channel connections for memory-efficient architecture search. arxiv preprint arXiv:1907.05737 (2022). https:\/\/arxiv.org\/abs\/1907.05737v1"},{"key":"4236_CR10","unstructured":"Vaswani, A., Shazeer, N., Parmar, N.: Attention is all you need. Advances in neural information processing systems, 30 (2017)"},{"key":"4236_CR11","unstructured":"Touvron, H., Cord. M., Douze, M.: Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning, PMLR. pp 10347\u201310357 (2021)"},{"key":"4236_CR12","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., Xiao, A., Wu, E.: Transformer in transformer. Adv. Neural. Inf. Process. Syst. 34, 15908\u201315919 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4236_CR13","unstructured":"Chu, X., Tian, Z., Zhang, B.: Conditional positional encodings for vision transformers. arxiv preprint arXiv:2102.10882 (2021)"},{"key":"4236_CR14","doi-asserted-by":"publisher","unstructured":"Kumari, N., Zhang, B., Zhang, R.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. Pp. 1931\u20131941 (2023). https:\/\/doi.org\/10.48550\/arXiv.2212.04488","DOI":"10.48550\/arXiv.2212.04488"},{"key":"4236_CR15","doi-asserted-by":"publisher","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H.: Swin transformer: hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10012\u201310022 (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.14030","DOI":"10.48550\/arXiv.2103.14030"},{"key":"4236_CR16","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., Tian, Z., Wang, Y.: Twins: revisiting the design of spatial attention in vision transformers. Adv. Neural. Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4236_CR17","doi-asserted-by":"publisher","unstructured":"Wang, W., Xie, E., Li, X.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV. Pp. 568\u2013578 (2021). https:\/\/doi.org\/10.48550\/arXiv.2102.12122","DOI":"10.48550\/arXiv.2102.12122"},{"key":"4236_CR18","doi-asserted-by":"publisher","unstructured":"Dong, X., Bao, J., Chen, D.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 12124\u201312134 (2022). https:\/\/doi.org\/10.48550\/arXiv.2107.00652","DOI":"10.48550\/arXiv.2107.00652"},{"key":"4236_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-025-03837-5","author":"P Chen","year":"2025","unstructured":"Chen, P., Cui, S., Cao, N.: Lightweight multi-scale feature fusion with attention guidance for passive non-line-of-sight imaging. Vis. Comput. (2025). https:\/\/doi.org\/10.1007\/s00371-025-03837-5","journal-title":"Vis. Comput."},{"key":"4236_CR20","doi-asserted-by":"crossref","unstructured":"Kwon, W., Kim, S., Mahoney, M. W., Hassoun, J., Keutzer, K., Gholami, A.: A fast post-training pruning framework for transformers. In: Advances in Neural Information Processing Systems, pp. 24101\u201324116 (2022)","DOI":"10.52202\/068431-1750"},{"key":"4236_CR21","doi-asserted-by":"crossref","unstructured":"Xu, K., Wang, Z., Chen, C., Geng, X., Lin, J., Yang, X., Wu, M., Li, X., Lin, W.: Lpvit: low-power semi-structured pruning for vision transformers. In: European Conference on Computer Vision, pp. 269\u2013287 (2024)","DOI":"10.1007\/978-3-031-73209-6_16"},{"key":"4236_CR22","doi-asserted-by":"publisher","unstructured":"Lin, Y., Zhang, T., Sun, P., Li, Z., Zhou, S.: Fq-vit: post-training quantization for fully quantized vision transformer. arxiv preprint arXiv:2111.13824 (2021). https:\/\/doi.org\/10.48550\/arXiv.2111.13824","DOI":"10.48550\/arXiv.2111.13824"},{"key":"4236_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2024.3422684","author":"H Shi","year":"2024","unstructured":"Shi, H., Cheng, X., Mao, W., Wang, Z.: P2-ViT: power-of-two post-training quantization and acceleration for fully quantized vision transformer. IEEE Trans. Very Large Scale Integr. Syst. (2024). https:\/\/doi.org\/10.1109\/TVLSI.2024.3422684","journal-title":"IEEE Trans. Very Large Scale Integr. Syst."},{"issue":"4","key":"4236_CR24","doi-asserted-by":"publisher","first-page":"e0267091","DOI":"10.1371\/journal.pone.0267091","volume":"17","author":"S Son","year":"2022","unstructured":"Son, S., Park, Y.C., Cho, M.: DAO-CP: data-adaptive online CP decomposition for tensor stream. PLoS ONE 17(4), e0267091 (2022)","journal-title":"PLoS ONE"},{"issue":"5","key":"4236_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3568682","volume":"17","author":"JG Jang","year":"2023","unstructured":"Jang, J.G., Kang, U.: Static and streaming tucker decomposition for dense tensors. ACM Trans. Knowl. Discov. Data 17(5), 1\u201334 (2023). https:\/\/doi.org\/10.1145\/3568682","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"4236_CR26","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H.: Svdiff: compact parameter space for diffusion fine-tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, pp. 7323\u20137334 (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"4236_CR27","doi-asserted-by":"publisher","unstructured":"Hu, EJ., Shen, Y., Wallis, P.: Lora: low-rank adaptation of large language models. arxiv preprint arXiv:2106.09685 (2021).https:\/\/doi.org\/10.48550\/arXiv.2106.09685","DOI":"10.48550\/arXiv.2106.09685"},{"key":"4236_CR28","doi-asserted-by":"publisher","unstructured":"Hajimolahoseini, H., Ahmed, W., Liu, Y.: Training acceleration of low-rank decomposed networks using sequential freezing and rank quantization. arxiv preprint arXiv:2309.03824 (2023). https:\/\/doi.org\/10.48550\/arXiv.2309.03824","DOI":"10.48550\/arXiv.2309.03824"},{"key":"4236_CR29","doi-asserted-by":"publisher","unstructured":"Xiao, J., Yin, M., Gong, Y.: COMCAT: towards efficient compression and customization of attention-based vision models. arxiv preprint arXiv:2305.17235 (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.17235","DOI":"10.48550\/arXiv.2305.17235"},{"issue":"2","key":"4236_CR30","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TNNLS.2021.3100554","volume":"34","author":"L Yuqiao","year":"2023","unstructured":"Yuqiao, L., Yanan, S., Bing, X., Mengjie, Z., Gary, Y., Kay, C.T.: A survey on evolutionary neural architecture search. IEEE Trans. Neural Netw. Learn. Syst. 34(2), 550\u2013570 (2023)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"4236_CR31","unstructured":"Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arxiv preprint arXiv:1806.09055 (2018)"},{"key":"4236_CR32","doi-asserted-by":"crossref","unstructured":"Wu, B., Dai, X., Zhang, P.: Fbnet: hardware-aware efficient convnet design via differentiable neural architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10734\u201310742 (2019)","DOI":"10.1109\/CVPR.2019.01099"},{"key":"4236_CR33","unstructured":"Tan, M., Le, Q.: Efficient net: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, PMLR. Pp. 6105\u20136114 (2019)"},{"key":"4236_CR34","doi-asserted-by":"publisher","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arxiv preprint arXiv:1611.01144 (2016). https:\/\/doi.org\/10.48550\/arxiv.1611.01144","DOI":"10.48550\/arxiv.1611.01144"},{"key":"4236_CR35","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R.: Imagenet: a large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4236_CR36","doi-asserted-by":"publisher","unstructured":"Jiahao, F., Shuchao, D., Xiaotian, S., Jiyuan, L., Yanan, S.: A gradient-based lightweight network automated design method for facial expression recognition. Expert Systems with Applications. 129130 (2025) https:\/\/doi.org\/10.1016\/j.eswa.2025.129130","DOI":"10.1016\/j.eswa.2025.129130"},{"key":"4236_CR37","unstructured":"Shi, D., Tao, C., Yang, Y.: Upop: Unified and progressive pruning for compressing vision-language transformers. In: International Conference on Machine Learning, PMLR, pp. 31292\u201331311 (2023)"},{"key":"4236_CR38","doi-asserted-by":"publisher","unstructured":"Bolya, D., Fu, CY., Dai, X.: Token merging: your vit but faster. arxiv preprint arXiv:2210.09461 (2022). https:\/\/doi.org\/10.48550\/arxiv.2210.09461","DOI":"10.48550\/arxiv.2210.09461"},{"key":"4236_CR39","doi-asserted-by":"crossref","unstructured":"Tang, Y., Han, K., Wang, Y.: Patch slimming for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 12165\u201312174 (2022)","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"4236_CR40","first-page":"19974","volume":"34","author":"T Chen","year":"2021","unstructured":"Chen, T., Cheng, Y., Gan, Z.: Chasing sparsity in vision transformers: An end-to-end exploration. Adv. Neural. Inf. Process. Syst. 34, 19974\u201319988 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4236_CR41","doi-asserted-by":"publisher","unstructured":"Yu, S., Chen, T., Shen, J.: Unified visual transformer compression. arxiv preprint. arXiv:2203.08243 (2022). https:\/\/doi.org\/10.48550\/arxiv.2210.09461","DOI":"10.48550\/arxiv.2210.09461"},{"key":"4236_CR42","first-page":"10936","volume":"33","author":"Y Tang","year":"2020","unstructured":"Tang, Y., Wang, Y., Xu, Y.: Scop: scientific control for reliable neural network pruning. Adv. Neural. Inf. Process. Syst. 33, 10936\u201310947 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4236_CR43","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., Liu, J.: Scalable vision transformers with hierarchical pooling. In: Proceedings of the IEEE\/cvf International Conference on Computer Vision, ICCV, pp. 377\u2013386 (2021)","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"4236_CR44","unstructured":"Goyal, S., Choudhury, AR., Raje, S.: Power-bert: accelerating bert inference via progressive word-vector elimination. In: International Conference on Machine Learning, PMLR, pp. 3690\u20133699 (2020)"},{"key":"4236_CR45","doi-asserted-by":"crossref","unstructured":"Yu, H., Wu, J.: Compressing transformers: features are low-rank, but weights are not!. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11007\u201311015 (2023)","DOI":"10.1609\/aaai.v37i9.26304"},{"key":"4236_CR46","doi-asserted-by":"crossref","unstructured":"Hou, Z., Kung, S. Y.: Multi-dimensional vision transformer compression via dependency guided gaussian process search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3669\u20133678 (2022)","DOI":"10.1109\/CVPRW56347.2022.00411"},{"key":"4236_CR47","doi-asserted-by":"publisher","unstructured":"Zhu, M., Tang, Y., Han, K.: Vision transformer pruning. arXiv preprint arXiv:2104.08500 (2021). https:\/\/doi.org\/10.48550\/arxiv.2104.08500","DOI":"10.48550\/arxiv.2104.08500"},{"key":"4236_CR48","first-page":"24898","volume":"34","author":"B Pan","year":"2021","unstructured":"Pan, B., Panda, R., Jiang, Y.: Ia-red2: interpretability-aware redundancy reduction for vision transformers. Adv. Neural. Inf. Process. Syst. 34, 24898\u201324911 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4236_CR49","doi-asserted-by":"publisher","unstructured":"Chua, T., S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: Nus-wide: a real-world web image database from national university of singapore. In: Proceedings of the ACM International Conference on Image and Video Retrieval, pp. 1\u20139 (2009). https:\/\/doi.org\/10.1145\/1646396.1646452","DOI":"10.1145\/1646396.1646452"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04236-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04236-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04236-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:02:28Z","timestamp":1772629348000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04236-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,11]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4236"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04236-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,11]]},"assertion":[{"value":"10 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"44"}}