{"id":4324,"date":"2023-11-06T22:44:41","date_gmt":"2023-11-06T21:44:41","guid":{"rendered":"https:\/\/www.ceessnoek.info\/?p=4324"},"modified":"2023-11-06T22:44:43","modified_gmt":"2023-11-06T21:44:43","slug":"neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion","status":"publish","type":"post","link":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/","title":{"rendered":"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion"},"content":{"rendered":"\n<p>The NeurIPS2023 cam-ready <em>ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion<\/em> by Yingjun Du, Zehao Xiao, Shengcai Liao, Cees G M Snoek is <a href=\"https:\/\/arxiv.org\/abs\/2306.14770\">now <\/a><a href=\"https:\/\/openreview.net\/pdf?id=lp9GR2t3hn\">available<\/a>. Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile process. To overcome this limitation, we introduce ProtoDiff, a novel framework that leverages a task-guided diffusion model during the meta-training phase to gradually generate prototypes, thereby providing efficient class representations. Specifically, a set of prototypes is optimized to achieve per-task prototype overfitting, enabling accurately obtaining the overfitted prototypes for individual tasks. Furthermore, we introduce a task-guided diffusion process within the prototype space, enabling the meta-learning of a generative process that transitions from a vanilla prototype to an overfitted prototype. ProtoDiff gradually generates task-specific prototypes from random noise during the meta-test stage, conditioned on the limited samples available for the new task. Furthermore, to expedite training and enhance ProtoDiff&#8217;s performance, we propose the utilization of residual prototype learning, which leverages the sparsity of the residual prototype. We conduct thorough ablation studies to demonstrate its ability to accurately capture the underlying prototype distribution and enhance generalization. The new state-of-the-art performance on within-domain, cross-domain, and few-task few-shot classification further substantiates the benefit of ProtoDiff.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1680\" height=\"422\" src=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png\" alt=\"\" class=\"wp-image-4251\" srcset=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png 1680w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff-300x75.png 300w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff-1024x257.png 1024w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff-768x193.png 768w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff-1536x386.png 1536w\" sizes=\"auto, (max-width: 1680px) 100vw, 1680px\" \/><\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>The NeurIPS2023 cam-ready ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion by Yingjun Du, Zehao Xiao, Shengcai Liao, Cees G M Snoek is now available. Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples [&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-4324","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>NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion - 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\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion - Cees Snoek\" \/>\n<meta property=\"og:description\" content=\"The NeurIPS2023 cam-ready ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion by Yingjun Du, Zehao Xiao, Shengcai Liao, Cees G M Snoek is now available. Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/\" \/>\n<meta property=\"og:site_name\" content=\"Cees Snoek\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-06T21:44:41+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-06T21:44:43+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.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\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/\",\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/\",\"name\":\"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion - Cees Snoek\",\"isPartOf\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png\",\"datePublished\":\"2023-11-06T21:44:41+00:00\",\"dateModified\":\"2023-11-06T21:44:43+00:00\",\"author\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#primaryimage\",\"url\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png\",\"contentUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.ceessnoek.info\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion\"}]},{\"@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":"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion - 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\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/","og_locale":"en_US","og_type":"article","og_title":"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion - Cees Snoek","og_description":"The NeurIPS2023 cam-ready ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion by Yingjun Du, Zehao Xiao, Shengcai Liao, Cees G M Snoek is now available. Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples [&hellip;]","og_url":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/","og_site_name":"Cees Snoek","article_published_time":"2023-11-06T21:44:41+00:00","article_modified_time":"2023-11-06T21:44:43+00:00","og_image":[{"url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.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\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/","url":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/","name":"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion - Cees Snoek","isPartOf":{"@id":"https:\/\/www.ceessnoek.info\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#primaryimage"},"image":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#primaryimage"},"thumbnailUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png","datePublished":"2023-11-06T21:44:41+00:00","dateModified":"2023-11-06T21:44:43+00:00","author":{"@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1"},"breadcrumb":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#primaryimage","url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png","contentUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/06\/du-protodiff.png"},{"@type":"BreadcrumbList","@id":"https:\/\/www.ceessnoek.info\/index.php\/neurips-2023-protodiff-learning-to-learn-prototypical-networks-by-task-guided-diffusion\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ceessnoek.info\/"},{"@type":"ListItem","position":2,"name":"NeurIPS 2023: ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion"}]},{"@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\/4324","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=4324"}],"version-history":[{"count":1,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4324\/revisions"}],"predecessor-version":[{"id":4325,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4324\/revisions\/4325"}],"wp:attachment":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/media?parent=4324"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/categories?post=4324"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/tags?post=4324"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}