{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T21:36:57Z","timestamp":1730237817273,"version":"3.28.0"},"reference-count":83,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.01777","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"19340-19351","source":"Crossref","is-referenced-by-count":1,"title":["Towards Inadequately Pre-trained Models in Transfer Learning"],"prefix":"10.1109","author":[{"given":"Andong","family":"Deng","sequence":"first","affiliation":[{"name":"University of Central Florida"}]},{"given":"Xingjian","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Research"}]},{"given":"Di","family":"Hu","sequence":"additional","affiliation":[{"name":"Renmin University of China"}]},{"given":"Tianyang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Alabama at Birmingham"}]},{"given":"Haoyi","family":"Xiong","sequence":"additional","affiliation":[{"name":"Baidu Research"}]},{"given":"Cheng-Zhong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Macau"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research","author":"Arpit"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"article-title":"Improved baselines with momentum contrastive learning","year":"2020","author":"Chen","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","article-title":"Catastrophic forgetting meets negative transfer: Batch spectral shrinkage for safe transfer learning","volume":"32","author":"Chen","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref11"},{"key":"ref12","first-page":"201","article-title":"Why does unsupervised pre-training help deep learning?","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Erhan"},{"key":"ref13","first-page":"153","article-title":"The difficulty of training deep architectures and the effect of unsupervised pre-training","volume-title":"Artificial Intelligence and Statistics","author":"Erhan","year":"2009"},{"article-title":"Unsupervised representation learning by predicting image rotations","year":"2018","author":"Gidaris","key":"ref14"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-68677-4","volume-title":"Artificial general intelligence","volume":"2","author":"Goertzel","year":"2007"},{"key":"ref16","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"International Conference on Machine Learning","author":"Hendrycks"},{"journal-title":"What makes imagenet good for transfer learning?","year":"2016","author":"Huh","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref23","article-title":"Sgd on neural networks learns functions of increasing complexity","volume":"32","author":"Kalimeris","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref30"},{"key":"ref31","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00632"},{"key":"ref33","first-page":"6010","article-title":"Rifle: Backpropagation in depth for deep transfer learning through re-initializing the fully-connected layer","volume-title":"International Conference on Machine Learning","author":"Li"},{"article-title":"Delta: Deep learning transfer using feature map with attention for convolutional networks","year":"2019","author":"Li","key":"ref34"},{"key":"ref35","article-title":"Towards explaining the regularization effect of initial large learning rate in training neural networks","volume":"32","author":"Li","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.08.001"},{"key":"ref38","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.4208\/csiam-am.so-2020-0005"},{"article-title":"Fine-grained visual classification of aircraft","year":"2013","author":"Maji","key":"ref40"},{"journal-title":"Do deep neural networks learn shallow learnable examples first?","year":"2019","author":"Mangalam","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2499239"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref44","first-page":"7294","article-title":"Leep: A new measure to evaluate transferability of learned representations","volume-title":"International Conference on Machine Learning","author":"Nguyen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00610"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"issue":"8","key":"ref52","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref53","article-title":"Transfusion: Understanding transfer learning for medical imaging","volume":"32","author":"Raghu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107252"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.4568"},{"issue":"602","key":"ref56","first-page":"2","article-title":"Mura dataset: Towards radiologist-level abnormality detection in musculoskeletal radiographs","volume":"1","author":"Rajpurkar","journal-title":"Hand"},{"article-title":"Do adversarially robust imagenet models transfer better?","year":"2020","author":"Salman","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00148"},{"key":"ref63","article-title":"Adversarially-trained deep nets transfer better: Illustration on image classification","author":"Utrera","year":"2021","journal-title":"ArXiv preprint arXiv:2007.05869"},{"issue":"11","key":"ref64","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref65","article-title":"The Caltech-UCSD Birds-200-2011 Dataset","volume-title":"Technical Report CNS-TR-2011-001","author":"Wah","year":"2011"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"ref67","article-title":"Aligning pretraining for detection via object-level contrastive learning","volume":"34","author":"Wei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.oa-2020-0085"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36708-4_22"},{"key":"ref71","first-page":"2825","article-title":"Explicit inductive bias for transfer learning with convolutional networks","volume-title":"International Conference on Machine Learning","author":"Xuhong"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"ref73","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-006-0663-2"},{"key":"ref75","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref76","article-title":"Logme: Practical assessment of pre-trained models for transfer learning","author":"You","year":"2021","journal-title":"ICML"},{"article-title":"Self-chained image-language model for video localization and question answering","year":"2023","author":"Yu","key":"ref77"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref79","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"International Conference on Machine Learning","author":"Zbontar"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"article-title":"Revisiting few-sample bert fine-tuning","volume-title":"International Conference on Learning Representations","author":"Zhang","key":"ref81"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref82"},{"key":"ref83","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Zoph","year":"2020"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2023,10,1]]},"location":"Paris, France","end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378023.pdf?arnumber=10378023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:42:56Z","timestamp":1705542176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10378023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.01777","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}