{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:12:07Z","timestamp":1777889527303,"version":"3.51.4"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00349","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3662-3672","source":"Crossref","is-referenced-by-count":0,"title":["SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency"],"prefix":"10.1109","author":[{"given":"Yangyang","family":"Guo","sequence":"first","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Semdedup: Data-efficient learning at web-scale through semantic deduplication","author":"Abbas","year":"2023","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","article-title":"Beit: BERT pre-training of image transformers","author":"Bao","year":"2022","journal-title":"ICLR. OpenReview.net"},{"key":"ref4","author":"Beaumont","year":"2022","journal-title":"Clip retrieval: Easily compute clip embeddings and build a clip retrieval system with them"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2000.895971"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","first-page":"3558","article-title":"Conceptual 12 m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts","author":"Changpinyo","year":"2021","journal-title":"CVPR"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref9","article-title":"Big self-supervised models are strong semi-supervised learners","author":"Chen","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref12","article-title":"Data distillation can be like vodka: Distilling more times for better quality","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR. OpenReview.net"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2950"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1063994968"},{"key":"ref17","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","author":"Evci","year":"2020","journal-title":"ICML"},{"key":"ref18","article-title":"Data filtering networks","author":"Fang","year":"2024","journal-title":"ICLR. OpenReview.net"},{"key":"ref19","article-title":"What neural networks memorize and why: Discovering the long tail via influence estimation","author":"Feldman","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref21","article-title":"A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation","author":"Gotmare","year":"2019","journal-title":"ICLR. OpenReview.net"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref27","article-title":"An empirical analysis of compute-optimal large language model training","author":"Hoffmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref28","author":"Ilharco","year":"2021","journal-title":"Openclip"},{"key":"ref29","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref30","article-title":"Scaling laws for neural language models","volume":"abs\/2001.08361","author":"Kaplan","year":"2020","journal-title":"CoRR"},{"key":"ref31","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","author":"Koh","year":"2017","journal-title":"ICML"},{"key":"ref32","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"issue":"7","key":"ref33","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref34","article-title":"Snip: single-shot network pruning based on connection sensitivity","author":"Lee","year":"2019","journal-title":"ICLR. OpenReview.net"},{"key":"ref35","article-title":"Error norm truncation: Robust training in the presence of data noise for text generation models","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref36","article-title":"UP-DP: unsupervised prompt learning for data pre-selection with vision-language models","author":"Li","year":"2023","journal-title":"In NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2132"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref39","first-page":"6989","article-title":"Do we actually need dense overparameterization? in-time over-parameterization in sparse training","author":"Liu","year":"2021","journal-title":"ICML"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","journal-title":"ICLR. OpenReview.net"},{"key":"ref42","article-title":"D2 pruning: Message passing for balancing diversity and difficulty in data pruning","author":"Maharana","year":"2024","journal-title":"ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02116"},{"key":"ref44","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","author":"Mirzasoleiman","year":"2020","journal-title":"ICML"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04316-3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/09540098908915626"},{"key":"ref47","article-title":"Fantastic weights and how to find them: Where to prune in dynamic sparse training","author":"Nowak","year":"2023","journal-title":"In NeurIPS"},{"key":"ref48","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"Ordonez","year":"2011","journal-title":"NIPS"},{"key":"ref49","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","author":"Paul","year":"2021","journal-title":"In NeurIPS"},{"key":"ref50","article-title":"Infobatch: Lossless training speed up by unbiased dynamic data pruning","author":"Qin","year":"2024","journal-title":"ICLR"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref52","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","author":"Recht","year":"2019","journal-title":"ICML"},{"key":"ref53","article-title":"Laion- 400 m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"NeurIPS Workshop Datacentric AI. J\u00fclich Supercomputing Center","author":"Schuhmann","year":"2021"},{"key":"ref54","article-title":"LAION5B: an open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0495"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref57","article-title":"Frequency domain-based dataset distillation","author":"Shin","year":"2023","journal-title":"NeurIPS"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/1036171"},{"key":"ref59","article-title":"Beyond neural scaling laws: beating power law scaling via data pruning","author":"Sorscher","year":"2022","journal-title":"NeurIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00897"},{"key":"ref61","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","author":"Tanaka","year":"2020","journal-title":"In NeurIPS"},{"key":"ref62","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021","journal-title":"ICML"},{"key":"ref63","author":"Van Den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00292"},{"key":"ref66","article-title":"Finetuned multimodal language models are high-quality image-text data filters","volume":"abs\/2403.02677","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref67","article-title":"Cliploss and norm-based data selection methods for multimodal contrastive learning","volume":"abs\/2405.19547","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref68","article-title":"On the de-duplication of LAION-2B","author":"Webster","year":"2023","journal-title":"CoRR"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01393"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1057\/9781137410405.0018"},{"key":"ref71","article-title":"Dataset pruning: Reducing training data by examining generalization influence","author":"Yang","year":"2023","journal-title":"ICLR"},{"key":"ref72","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"TMLPR"},{"key":"ref73","first-page":"20838","article-title":"MEST: accurate and fast memoryeconomic sparse training framework on the edge","author":"Yuan","year":"2021","journal-title":"NeurIPS"},{"key":"ref74","article-title":"Dynamic sparse no training: Training-free fine-tuning for sparse 11 ms","author":"Zhang","year":"2024","journal-title":"ICLR"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446265.pdf?arnumber=11446265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:22Z","timestamp":1777612342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00349","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}