{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:41:22Z","timestamp":1743104482186,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031208676"},{"type":"electronic","value":"9783031208683"}],"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\/978-3-031-20868-3_18","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:29:12Z","timestamp":1667518152000},"page":"240-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Training a\u00a0Lightweight ViT Network for\u00a0Image Retrieval"],"prefix":"10.1007","author":[{"given":"Hanqi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Bhojanapalli, S., Chakrabarti, A., Glasner, D., Li, D., Unterthiner, T., Veit, A.: Understanding robustness of transformers for image classification. In: ICCV, pp. 10231\u201310241 (2021)","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: Crossvit: Cross-attention multi-scale vision transformer for image classification. In: ICCV, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"18_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: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. ICLR (2021)"},{"key":"18_CR6","unstructured":"El-Nouby, A., Neverova, N., Laptev, I., J\u00e9gou, H.: Training vision transformers for image retrieval. arXiv preprint arXiv:2102.05644 (2021)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR, pp. 1735\u20131742 (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"18_CR8","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: A survey. arXiv preprint arXiv:2102.04906 (2021)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: CVPR, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, D., Cho, M., Kwak, S.: Proxy anchor loss for deep metric learning. In: CVPR, pp. 3238\u20133247 (2020)","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, D., Cho, M., Kwak, S.: Embedding transfer with label relaxation for improved metric learning. In: CVPR, pp. 3967\u20133976 (2021)","DOI":"10.1109\/CVPR46437.2021.00396"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: ICCV (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"18_CR13","unstructured":"Li, Z., Yang, T., Wang, P., Cheng, J.: Q-vit: Fully differentiable quantization for vision transformer. arXiv preprint arXiv:2201.07703 (2022)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR15","unstructured":"Liu, Z., Wang, Y., Han, K., Ma, S., Gao, W.: Post-training quantization for vision transformer. NeurIPS (2021)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: CVPR, pp. 1096\u20131104 (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"18_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. ICLR (2017)"},{"key":"18_CR18","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Oh Song, H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: CVPR, pp. 4004\u20134012 (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Sabet, A., Hare, J., Al-Hashimi, B., Merrett, G.V.: Temporal early exits for efficient video object detection. arXiv preprint arXiv:2106.11208 (2021)","DOI":"10.2139\/ssrn.4001359"},{"issue":"5","key":"18_CR21","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1007\/s12559-020-09734-4","volume":"12","author":"S Scardapane","year":"2020","unstructured":"Scardapane, S., Scarpiniti, M., Baccarelli, E., Uncini, A.: Why should we add early exits to neural networks? Cognitive Computation 12(5), 954\u2013966 (2020)","journal-title":"Cognitive Computation"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: Transformer for semantic segmentation. In: ICCV, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"18_CR23","unstructured":"Tolstikhin, I., et al.: Mlp-mixer: An all-mlp architecture for vision. arXiv preprint arXiv:2105.01601 (2021)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Touvron, H., et al.: Resmlp: Feedforward networks for image classification with data-efficient training. arXiv preprint arXiv:2105.03404 (2021)","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"18_CR25","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"18_CR26","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset. Tech. rep. (2011)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token vit: Training vision transformers from scratch on imagenet. In: ICCV, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lu, X., Cao, G., Yang, Y., Jiao, L., Liu, F.: Vit-yolo: Transformer-based yolo for object detection. In: ICCV, pp. 2799\u20132808 (2021)","DOI":"10.1109\/ICCVW54120.2021.00314"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2022: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20868-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T06:17:29Z","timestamp":1728281849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20868-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031208676","9783031208683"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20868-3_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":"4 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shangai","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pricai.org\/2022\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"432","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":"91","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":"39","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":"21% - 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":"7-8","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":"n\/a","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)"}}]}}