{"id":4011,"date":"2022-03-28T20:54:23","date_gmt":"2022-03-28T19:54:23","guid":{"rendered":"https:\/\/www.ceessnoek.info\/?p=4011"},"modified":"2022-03-28T20:55:09","modified_gmt":"2022-03-28T19:55:09","slug":"iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains","status":"publish","type":"post","link":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/","title":{"rendered":"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains"},"content":{"rendered":"\n<p>The ICLR 2022 paper <em>Hierarchical Variational Memory for Few-shot Learning Across Domains<\/em> by Yingjun Du, Xiantong Zhen, Ling Shao and Cees G M Snoek is now <a href=\"https:\/\/openreview.net\/pdf?id=i3RI65sR7N\">available<\/a>. Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not generalize well in presence of a domain shift between training and test distributions. Rather than relying on a flat memory, we propose a hierarchical alternative that stores features at different semantic levels. We introduce a hierarchical prototype model, where each level of the prototype fetches corresponding information from the hierarchical memory. The model is endowed with the ability to flexibly rely on features at different semantic levels if the domain shift circumstances so demand. We meta-learn the model by a newly derived hierarchical variational inference framework, where hierarchical memory and prototypes are jointly optimized. To explore and exploit the importance of different semantic levels, we further propose to learn the weights associated with the prototype at each level in a data-driven way, which enables the model to adaptively choose the most generalizable features. We conduct thorough ablation studies to demonstrate the effectiveness of each component in our model. The new state-of-the-art performance on cross-domain and competitive performance on traditional few-shot classification further substantiates the benefit of hierarchical variational memory.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1034\" height=\"770\" src=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png\" alt=\"\" class=\"wp-image-3943\" srcset=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png 1034w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical-300x223.png 300w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical-1024x763.png 1024w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical-768x572.png 768w\" sizes=\"auto, (max-width: 1034px) 100vw, 1034px\" \/><\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>The ICLR 2022 paper Hierarchical Variational Memory for Few-shot Learning Across Domains by Yingjun Du, Xiantong Zhen, Ling Shao and Cees G M Snoek is now available. Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-4011","post","type-post","status-publish","format-standard","hentry","category-science"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains - Cees Snoek<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains - Cees Snoek\" \/>\n<meta property=\"og:description\" content=\"The ICLR 2022 paper Hierarchical Variational Memory for Few-shot Learning Across Domains by Yingjun Du, Xiantong Zhen, Ling Shao and Cees G M Snoek is now available. Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/\" \/>\n<meta property=\"og:site_name\" content=\"Cees Snoek\" \/>\n<meta property=\"article:published_time\" content=\"2022-03-28T19:54:23+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-03-28T19:55:09+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png\" \/>\n<meta name=\"author\" content=\"Cees\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Cees\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/\",\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/\",\"name\":\"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains - Cees Snoek\",\"isPartOf\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png\",\"datePublished\":\"2022-03-28T19:54:23+00:00\",\"dateModified\":\"2022-03-28T19:55:09+00:00\",\"author\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#primaryimage\",\"url\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png\",\"contentUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png\",\"width\":1034,\"height\":770},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.ceessnoek.info\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.ceessnoek.info\/#website\",\"url\":\"https:\/\/www.ceessnoek.info\/\",\"name\":\"Cees Snoek\",\"description\":\"research on video and image ai\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.ceessnoek.info\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\",\"name\":\"Cees\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g\",\"caption\":\"Cees\"},\"sameAs\":[\"http:\/\/www.CeesSnoek.info\"],\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/author\/admin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains - Cees Snoek","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/","og_locale":"en_US","og_type":"article","og_title":"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains - Cees Snoek","og_description":"The ICLR 2022 paper Hierarchical Variational Memory for Few-shot Learning Across Domains by Yingjun Du, Xiantong Zhen, Ling Shao and Cees G M Snoek is now available. Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not [&hellip;]","og_url":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/","og_site_name":"Cees Snoek","article_published_time":"2022-03-28T19:54:23+00:00","article_modified_time":"2022-03-28T19:55:09+00:00","og_image":[{"url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png","type":"","width":"","height":""}],"author":"Cees","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Cees","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/","url":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/","name":"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains - Cees Snoek","isPartOf":{"@id":"https:\/\/www.ceessnoek.info\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#primaryimage"},"image":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#primaryimage"},"thumbnailUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png","datePublished":"2022-03-28T19:54:23+00:00","dateModified":"2022-03-28T19:55:09+00:00","author":{"@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1"},"breadcrumb":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#primaryimage","url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png","contentUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/12\/du-hierarchical.png","width":1034,"height":770},{"@type":"BreadcrumbList","@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr-2022-hierarchical-variational-memory-for-few-shot-learning-across-domains\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ceessnoek.info\/"},{"@type":"ListItem","position":2,"name":"ICLR 2022: Hierarchical Variational Memory for Few-shot Learning Across Domains"}]},{"@type":"WebSite","@id":"https:\/\/www.ceessnoek.info\/#website","url":"https:\/\/www.ceessnoek.info\/","name":"Cees Snoek","description":"research on video and image ai","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.ceessnoek.info\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1","name":"Cees","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g","caption":"Cees"},"sameAs":["http:\/\/www.CeesSnoek.info"],"url":"https:\/\/www.ceessnoek.info\/index.php\/author\/admin\/"}]}},"_links":{"self":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4011","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/comments?post=4011"}],"version-history":[{"count":1,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4011\/revisions"}],"predecessor-version":[{"id":4012,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4011\/revisions\/4012"}],"wp:attachment":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/media?parent=4011"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/categories?post=4011"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/tags?post=4011"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}