{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:48:05Z","timestamp":1777902485031,"version":"3.51.4"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Transfer learning has made significant advancements, however, the issue of overfitting continues to pose a major challenge. Data augmentation has emerged as a highly promising technique to counteract this challenge. Current data augmentation methods are fixed in nature, requiring manual determination of the appropriate intensity prior to the training process. However, this entails substantial computational costs. Additionally, as the model approaches convergence, static data augmentation strategies can become suboptimal. In this paper, we introduce the concept of Dynamic Data Augmentation (DynamicAug), a method that autonomously adjusts the intensity of data augmentation, taking into account the convergence state of the model. During each iteration of the model\u2019s forward pass, we utilize a Gaussian distribution based sampler to stochastically sample the current intensity of data augmentation. To ensure that the sampled intensity is aligned with the convergence state of the model, we introduce a learnable expectation to the sampler and update the expectation iteratively. In order to assess the convergence status of the model, we introduce a novel loss function called the convergence loss. Through extensive experiments conducted over 27 vision datasets, we have demonstrated that DynamicAug can significantly enhance the performance of existing transfer learning methods.<\/jats:p>","DOI":"10.1007\/s11063-024-11626-9","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T03:01:37Z","timestamp":1716174097000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DynamicAug: Enhancing Transfer Learning Through Dynamic Data Augmentation Strategies Based on Model State"],"prefix":"10.1007","volume":"56","author":[{"given":"Xinyi","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linlin","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,20]]},"reference":[{"issue":"6","key":"11626_CR1","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.3390\/app10062021","volume":"10","author":"I Kandel","year":"2020","unstructured":"Kandel I, Castelli M (2020) Transfer learning with convolutional neural networks for diabetic retinopathy image classification. A review. Appl Sci 10(6):2021","journal-title":"Appl Sci"},{"key":"11626_CR2","doi-asserted-by":"publisher","first-page":"146533","DOI":"10.1109\/ACCESS.2019.2946000","volume":"7","author":"C Wang","year":"2019","unstructured":"Wang C, Chen D, Hao L, Liu X, Zeng Y, Chen J, Zhang G (2019) Pulmonary image classification based on inception-v3 transfer learning model. IEEE Access 7:146533\u2013146541","journal-title":"IEEE Access"},{"key":"11626_CR3","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo W-Y et al (2023) Segment anything. arXiv preprint arXiv:2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"11626_CR4","unstructured":"Oquab M, Darcet T, Moutakanni T, Vo H, Szafraniec M, Khalidov V, Fernandez P, Haziza D, Massa F, El-Nouby A et al (2023) Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193"},{"key":"11626_CR5","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: ECCV. Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"11626_CR6","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask R-CNN. In: ICCV, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"issue":"4","key":"11626_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI 40(4):834\u2013848","journal-title":"TPAMI"},{"key":"11626_CR8","unstructured":"Zhu D, Chen J, Shen X, Li X, Elhoseiny M (2023) MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592"},{"key":"11626_CR9","unstructured":"Kwon W, Li Z, Zhuang S, Sheng Y, Zheng L, Yu C, Gonzalez J, Zhang H et al (2023) vLLM: easy, fast, and cheap LLM serving with PagedAttention"},{"key":"11626_CR10","doi-asserted-by":"crossref","unstructured":"Jia M, Tang L, Chen B-C, Cardie C, Belongie S, Hariharan B, Lim S-N (2022) Visual prompt tuning. In: ECCV","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"11626_CR11","first-page":"16664","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen S, Ge C, Tong Z, Wang J, Song Y, Wang J, Luo P (2022) AdaptFormer: adapting vision transformers for scalable visual recognition. Adv Neural Inf Process Syst 35:16664\u201316678","journal-title":"Adv Neural Inf Process Syst"},{"key":"11626_CR12","unstructured":"Jie S, Deng Z-H (2022) Convolutional bypasses are better vision transformer adapters. arXiv preprint arXiv:2207.07039"},{"key":"11626_CR13","unstructured":"Zhang Y, Zhou K, Liu Z (2022) Neural prompt search. arXiv preprint arXiv:2206.04673"},{"key":"11626_CR14","unstructured":"Zhai X, Puigcerver J, Kolesnikov A, Ruyssen P, Riquelme C, Lucic M, Djolonga J, Pinto AS, Neumann M, Dosovitskiy A et al (2019) A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867"},{"key":"11626_CR15","unstructured":"Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2017) mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412"},{"key":"11626_CR16","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ, Chun S, Choe J, Yoo Y (2019) CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"},{"key":"11626_CR17","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Shlens J, Le QV (2020) Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 702\u2013703","DOI":"10.1109\/CVPRW50498.2020.00359"},{"issue":"1","key":"11626_CR18","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"11626_CR19","unstructured":"Luo G, Huang M, Zhou Y, Sun X, Jiang G, Wang Z, Ji R (2023) Towards efficient visual adaption via structural re-parameterization. arXiv preprint arXiv:2302.08106"},{"key":"11626_CR20","unstructured":"Khosla A, Jayadevaprakash N, Yao B, Fei-Fei L (2011) Novel dataset for fine-grained image categorization. In: CVPRW"},{"key":"11626_CR21","doi-asserted-by":"crossref","unstructured":"Nilsback M-E, Zisserman A (2008) Automated flower classification over a large number of classes. In: ICVGIP. IEEE, pp 722\u2013729","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"11626_CR22","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn G, Branson S, Farrell R, Haber S, Barry J, Ipeirotis P, Perona P, Belongie S (2015) Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection. In: CVPR, pp 595\u2013604","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"11626_CR23","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The Caltech-UCSD birds-200-2011 dataset. Tech. Rep. CNS-TR-2011-001, California Institute of Technology"},{"key":"11626_CR24","unstructured":"Zhai X, Puigcerver J, Kolesnikov A, Ruyssen P, Riquelme C, Lucic M, Djolonga J, Pinto AS, Neumann M, Dosovitskiy A et al (2019) A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867"},{"key":"11626_CR25","doi-asserted-by":"crossref","unstructured":"He H, Cai J, Zhang J, Tao D, Zhuang B (2023) Sensitivity-aware visual parameter-efficient tuning. arXiv preprint arXiv:2303.08566","DOI":"10.1109\/ICCV51070.2023.01086"},{"key":"11626_CR26","unstructured":"Hu EJ, shen, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2022) LoRA: low-rank adaptation of large language models. In: ICLR"},{"key":"11626_CR27","unstructured":"Houlsby N, Giurgiu A, Jastrzebski S, Morrone B, De\u00a0Laroussilhe Q, Gesmundo A, Attariyan M, Gelly S (2019) Parameter-efficient transfer learning for NLP. In: ICML, pp 2790\u20132799"},{"issue":"3","key":"11626_CR28","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1007\/s10462-021-10066-4","volume":"55","author":"NE Khalifa","year":"2022","unstructured":"Khalifa NE, Loey M, Mirjalili S (2022) A comprehensive survey of recent trends in deep learning for digital images augmentation. Artif Intell Rev 55(3):2351\u20132377","journal-title":"Artif Intell Rev"},{"key":"11626_CR29","unstructured":"Larsson G, Maire M, Shakhnarovich G (2016) FractalNet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648"},{"key":"11626_CR30","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Mane D, Vasudevan V, Le QV (2018) Autoaugment: learning augmentation policies from data. arXiv preprint arXiv:1805.09501","DOI":"10.1109\/CVPR.2019.00020"},{"key":"11626_CR31","unstructured":"He J, Zhou C, Ma X, Berg-Kirkpatrick T, Neubig G (2022) Towards a unified view of parameter-efficient transfer learning. In: ICLR"},{"key":"11626_CR32","doi-asserted-by":"crossref","unstructured":"Zhong Z, Friedman D, Chen D (2021) Factual probing is [mask]: learning vs. learning to recall. arXiv preprint arXiv:2104.05240","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"issue":"9","key":"11626_CR33","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou K, Yang J, Loy CC, Liu Z (2022) Learning to prompt for vision-language models. IJCV 130(9):2337\u20132348","journal-title":"IJCV"},{"key":"11626_CR34","doi-asserted-by":"crossref","unstructured":"Caelles S, Maninis K-K, Pont-Tuset J, Leal-Taix\u00e9 L, Cremers D, Van\u00a0Gool L (2017) One-shot video object segmentation. In: CVPR, pp 221\u2013230","DOI":"10.1109\/CVPR.2017.565"},{"key":"11626_CR35","first-page":"7","volume":"2","author":"J Yosinski","year":"2014","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? NeurIPS 2:7","journal-title":"NeurIPS"},{"key":"11626_CR36","doi-asserted-by":"crossref","unstructured":"Zaken EB, Goldberg Y, Ravfogel S (2022) BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: ACL, pp 1\u20139","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"11626_CR37","unstructured":"Liu Z, Xu Z, Jin J, Shen Z, Darrell T (2023) Dropout reduces underfitting. arXiv preprint arXiv:2303.01500"},{"key":"11626_CR38","unstructured":"Li B, Hu Y, Nie X, Han C, Jiang X, Guo T, Liu L (2022) Dropkey. arXiv preprint arXiv:2208.02646"},{"key":"11626_CR39","doi-asserted-by":"crossref","unstructured":"Liu Z, Cheng K-T, Huang D, Xing EP, Shen Z (2022) Nonuniform-to-uniform quantization: towards accurate quantization via generalized straight-through estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4942\u20134952","DOI":"10.1109\/CVPR52688.2022.00489"},{"key":"11626_CR40","doi-asserted-by":"crossref","unstructured":"Hu S, Xie S, Zheng H, Liu C, Shi J, Liu X, Lin D (2020) DSNAS: direct neural architecture search without parameter retraining. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12084\u201312092","DOI":"10.1109\/CVPR42600.2020.01210"},{"key":"11626_CR41","doi-asserted-by":"crossref","unstructured":"Gebru T, Krause J, Wang Y, Chen D, Deng J, Fei-Fei L (2017) Fine-grained car detection for visual census estimation. In: AAAI","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"11626_CR42","doi-asserted-by":"crossref","unstructured":"Bossard L, Guillaumin M, Gool LV (2014) Food-101\u2013mining discriminative components with random forests. In: European conference on computer vision (ECCV). Springer, pp 446\u2013461","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"11626_CR43","unstructured":"Nilsback M-E, Zisserman A (2006) A visual vocabulary for flower classification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), vol 2. IEEE, pp 1447\u20131454"},{"key":"11626_CR44","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Fei-Fei L (2013) 3d object representations for fine-grained categorization. In: Proceedings of the IEEE international conference on computer vision workshops, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"11626_CR45","doi-asserted-by":"crossref","unstructured":"Parkhi OM, Vedaldi A, Zisserman A, Jawahar C (2012) Cats and dogs. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). IEEE, pp 3498\u20133505","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"11626_CR46","unstructured":"Maji S, Rahtu E, Kannala J, Blaschko M, Vedaldi A (2013) Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151"},{"key":"11626_CR47","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision. In: ICML, pp 8748\u20138763"},{"key":"11626_CR48","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: CVPR, pp 16000\u201316009","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"11626_CR49","doi-asserted-by":"crossref","unstructured":"Chen X, Xie S, He K (2021) An empirical study of training self-supervised vision transformers. In: ICCV, pp 9640\u20139649","DOI":"10.1109\/ICCV48922.2021.00950"},{"issue":"2","key":"11626_CR50","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2023","unstructured":"Gao P, Geng S, Zhang R, Ma T, Fang R, Zhang Y, Li H, Qiao Y (2023) Clip-adapter: better vision-language models with feature adapters. Int J Comput Vis 132(2):581\u2013595","journal-title":"Int J Comput Vis"},{"key":"11626_CR51","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision. In: International conference on machine learning. PMLR, pp 8748\u20138763"},{"key":"11626_CR52","unstructured":"Loshchilov I, Hutter F (2018) Fixing weight decay regularization in Adam. https:\/\/openreview.net\/forum?id=rk6qdGgCZ"},{"key":"11626_CR53","doi-asserted-by":"crossref","unstructured":"Biswas M, Buckchash H, Prasad DK (2023) pNNCLR: stochastic pseudo neighborhoods for contrastive learning based unsupervised representation learning problems. arXiv preprint arXiv:2308.06983","DOI":"10.1016\/j.neucom.2024.127810"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11626-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11626-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11626-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T07:20:44Z","timestamp":1721028044000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11626-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":53,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["11626"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11626-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3573401\/v1","asserted-by":"object"}]},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,20]]},"assertion":[{"value":"15 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"176"}}