{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:59:06Z","timestamp":1783439946700,"version":"3.54.6"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076067"],"award-info":[{"award-number":["62076067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]},{"name":"ZJ Lab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3223784","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:18:47Z","timestamp":1669065527000},"page":"7639-7653","source":"Crossref","is-referenced-by-count":21,"title":["PatchMix Augmentation to Identify Causal Features in Few-Shot Learning"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3891-2227","authenticated-orcid":false,"given":"Chengming","family":"Xu","sequence":"first","affiliation":[{"name":"School of Data Science and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6962-7985","authenticated-orcid":false,"given":"Xinwei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Data Science and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siqian","family":"Yang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-8090","authenticated-orcid":false,"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6595-6893","authenticated-orcid":false,"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Data Science and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref3","first-page":"4080","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Snell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref5","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref6","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Hou"},{"key":"ref7","volume-title":"Probabilistic Machine Learning: Advanced Topics","author":"Murphy","year":"2022"},{"key":"ref8","article-title":"Noise or signal: The role of image backgrounds in object recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao"},{"key":"ref9","article-title":"The pitfalls of simplicity bias in neural networks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Shah"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445883"},{"key":"ref11","first-page":"2734","article-title":"Interventional few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yue"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref13","article-title":"Unsupervised learning via meta-learning","author":"Hsu","year":"2018"},{"key":"ref14","article-title":"On the role of neural collapse in transfer learning","author":"Galanti","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"ref16","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi"},{"key":"ref17","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref18","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"Li","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref20","article-title":"Meta-learning with latent embedding optimization","author":"Rusu","year":"2018"},{"key":"ref21","first-page":"10276","article-title":"Learning to self-train for semi-supervised few-shot classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00053"},{"key":"ref23","first-page":"4847","article-title":"Adaptive cross-modal few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xing"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86340-1_39"},{"key":"ref27","article-title":"Bayesian few-shot classification with one-vs-each p\\\u2019olya-gamma augmented Gaussian processes","author":"Snell","year":"2020"},{"key":"ref28","article-title":"MELR: Meta-learning via modeling episode-level relationships for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fei"},{"key":"ref29","article-title":"IEPT: Instance-level and episode-level pretext tasks for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"ref31","article-title":"BOIL: Towards representation change for few-shot learning","author":"Oh","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_15"},{"key":"ref34","article-title":"A baseline for few-shot image classification","author":"Dhillon","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01348"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00177"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00760"},{"key":"ref39","article-title":"Delta-encoder: An effective sample synthesis method for few-shot object recognition","author":"Schwartz","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_35"},{"key":"ref41","article-title":"Free lunch for few-shot learning: Distribution calibration","author":"Yang","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref44","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2019"},{"key":"ref45","article-title":"A person re-identification data augmentation method with adversarial defense effect","author":"Gong","year":"2021"},{"key":"ref46","article-title":"Gridmask data augmentation","author":"Chen","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093338"},{"key":"ref50","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref51","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref53","first-page":"16846","article-title":"Recovering latent causal factor for generalization to distributional shifts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12167"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1732"},{"key":"ref56","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"Pearl","year":"2009"},{"key":"ref57","volume-title":"Models, Reasoning and Inference","volume":"19","author":"Pearl","year":"2000"},{"key":"ref58","first-page":"719","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Oreshkin"},{"key":"ref59","first-page":"2207","article-title":"Variational autoencoders and nonlinear ICA: A unifying framework","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Khemakhem"},{"key":"ref60","first-page":"249","article-title":"Identifying confounders using additive noise models","volume-title":"Proc. 25th Conf. Uncertainty Artif. Intell.","author":"Janzing"},{"key":"ref61","first-page":"2009","article-title":"Causal discovery with continuous additive noise models","volume":"15","author":"Peters","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref62","first-page":"9458","article-title":"Few-shot domain adaptation by causal mechanism transfer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Teshima"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref64","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_10"},{"key":"ref67","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref68","article-title":"Unsupervised meta-learning for few-shot image classification","author":"Khodadadeh","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref70","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Vinyals"},{"key":"ref71","article-title":"Meta-learning for semi-supervised few-shot classification","author":"Ren","year":"2018"},{"key":"ref72","article-title":"Meta-learning with differentiable closed-form solvers","author":"Bertinetto","year":"2018"},{"key":"ref73","article-title":"Caltech-UCSD Birds 200","author":"Welinder","year":"2010"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref77","article-title":"Cross-domain few-shot classification via learned feature-wise transformation","author":"Tseng","year":"2020"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref79","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00755"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00382"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00011"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00815"},{"key":"ref85","first-page":"7115","article-title":"TapNet: Neural network augmented with task-adaptive projection for few-shot learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_24"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_26"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref91","article-title":"Attentional constellation nets for few-shot learning","author":"Xu","year":"2021"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00514"},{"key":"ref93","article-title":"Few-shot learning with graph neural networks","author":"Garcia","year":"2017"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412941"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09956886.pdf?arnumber=9956886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:57:11Z","timestamp":1706756231000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":94,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3223784","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}