[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120644-en":3,"doc-seo-120644-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120644,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Learning from Very Few Samples - A Survey","Few sample learning (FSL) addresses a central challenge in machine learning: achieving accurate learning and generalization from only one or a handful of labeled examples. Contrasting human rapid cognition from minimal observations, conventional algorithms often require hundreds or thousands of supervised samples to perform reliably. This survey reviews 200+ FSL papers from the 2000s to 2019, tracing historical evolution and summarizing current progress. It organizes approaches into generative and discriminative categories, highlights meta-learning based methods, discusses emerging extension topics, and covers key applications across computer vision, NLP, audio, speech, reinforcement learning, robotics, and data analysis, concluding with promising future trends.","arXiv :2009 .02653v 1 [ cs .LG] 6 Sep 2020  \nLearning from Very Few Samples: A Survey  \nJiang Lu, Pinghua Gong, Jieping Ye, Fellow, IEEE , and Changshui Zhang, Fellow, IEEE  \nAbstract—Few sample learning (FSL) is significant and challenging in the field of machine learning. The capability of learning and generalizing from very few samples successfully is a noticeable demarcation separating artificial intelligence and human intelligence since humans can readily establish their cognition to novelty from just a single or a handful of examples whereas machine learning algorithms typically entail hundreds or thousands of supervised samples to guarantee generalization ability. Despite the long history dated back to the early 2000s and the widespread attention in recent years with booming deep learning technologies, little surveys or reviews for FSL are available until now. In this context, we extensively review 200+ papers of FSL spanning from the 2000s to 2019 and provide a timely and comprehensive survey for FSL. In this survey, we review the evolution history as well as the current progress on FSL, categorize FSL approaches into the generative model based and discriminative model based kinds in principle, and emphasize particularly on the meta learning based FSL approaches. We also summarize several recently emerging extensional topics of FSL and review the latest advances on these topics. Furthermore, we highlight the important FSL applications covering many research hotspots in computer vision, natural language processing, audio and speech, reinforcement learning and robotic, data analysis, etc. Finally, we conclude the survey with a discussion on promising trends in the hope of providing guidance and insights to follow-up researches.  \nIndex Terms—few sample learning, learn to learn, survey, few-shot learning, meta learning  \n~~ ~~ F ~~ ~~  \n1 INTRODUCTION  \nONE impressive hallmark of human intelligence is the  \nability to rapidly establish cognition to novel concepts from just a single or a handful of examples. Many cognitive and psychological evidences [1], [2], [3] have shown that humans can recognize visual objects through very few images [4] and even children can remember a novel word by a single encounter [5],[6] . Although exactly what support the human capability of learning and generalizing from very few samples remains a profound mystery, some neurobiological works [7], [8], [9] have argued that the prominent human learning ability benefits from prefrontal cortex (PFC) and working memory in human brain, especially the interaction between PFC-specific neurobiological mechanism and previous experience stored in the brain. By contrast, most cuttingedge machine learning algorithms are data-hungry, especially the most widely known deep learning [10] that has pushed artificial intelligence to a new climax. As an important milestone in the development of machine learning, deep learning has scored remarkable achievement in a broad spectrum of research fields including vision [11],[12],[13], language [14],[15], speech [16], game [17], demography [18], medicine [19], phytopathology [20] and zoology [21], etc. Generally, the successes of deep learning can be owned to three key factors: powerful computing resources (e.g., GPU), sophisticated neural networks (e.g., CNN [11], LSTM [22]) and large-scale datasets (e.g., ImageNet [23], Pascal-VOC [24]) . However, many realistic application scenarios, such as in the field  \n􀀏 J. Lu and C. Zhang are with the Institute for Artificial Intelligence, Tsinghua University (THUAI), the State Key Laboratory of Intelligence Technologies and Systems, the Beijing National Research Center for Information Science and Technologies (BNRist) , the Department of Automation, Tsinghua University, Beijing 100084, China. E-mail: lu[j13@tsinghua.org.cn](j13@tsinghua.org.cn); [zcs@mail.tsinghua.edu.cn](zcs@mail.tsinghua.edu.cn).  \n􀀏 P. Gong is with the Didi Research Institute, Didi Chuxing, Beijing 100085, [China. E-","cbCaivCuzDps4aE0","https://ap.wps.com/l/cbCaivCuzDps4aE0","pdf",19549582,1,30,"English","en",105,"# Introduction\n## Motivation and significance of few sample learning\n## Challenges and optimization viewpoint\n## Survey scope and organization","[{\"question\":\"Why is few sample learning considered important in machine learning?\",\"answer\":\"FSL aims to learn and generalize with minimal labeled data, reducing dependence on large training sets and enabling low-cost, quick model deployment for tasks where only few samples are available.\"},{\"question\":\"How does the survey structure few sample learning approaches?\",\"answer\":\"It reviews historical progress and categorizes FSL approaches mainly into generative-model-based and discriminative-model-based methods, with emphasis on meta learning based FSL.\"},{\"question\":\"What application areas does the survey highlight for few sample learning?\",\"answer\":\"It summarizes important FSL applications across computer vision, natural language processing, audio and speech, reinforcement learning and robotics, and data analysis.\"}]","Learning from Very Few Samples - A Survey | PDF",1785731074,76,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"learning-from-very-few-samples-a-survey","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/learning-from-very-few-samples-a-survey/120644/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is few sample learning considered important in machine learning?","Question",{"text":75,"@type":76},"FSL aims to learn and generalize with minimal labeled data, reducing dependence on large training sets and enabling low-cost, quick model deployment for tasks where only few samples are available.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the survey structure few sample learning approaches?",{"text":80,"@type":76},"It reviews historical progress and categorizes FSL approaches mainly into generative-model-based and discriminative-model-based methods, with emphasis on meta learning based FSL.",{"name":82,"@type":73,"acceptedAnswer":83},"What application areas does the survey highlight for few sample learning?",{"text":84,"@type":76},"It summarizes important FSL applications across computer vision, natural language processing, audio and speech, reinforcement learning and robotics, and data analysis.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":21,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]