{"id":855,"date":"2023-02-10T16:53:04","date_gmt":"2023-02-10T16:53:04","guid":{"rendered":"https:\/\/www.allendowney.com\/blog\/?p=855"},"modified":"2023-02-10T16:53:04","modified_gmt":"2023-02-10T16:53:04","slug":"dont-discard-that-pangolin","status":"publish","type":"post","link":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/","title":{"rendered":"Don&#8217;t discard that pangolin"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Sadly, today is my last day at DrivenData, so it&#8217;s a good time to review one of the projects I&#8217;ve been working on, using probabilistic predictions from Zamba to find animals in camera trap videos, like this:<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<span class=\"embed-youtube\" style=\"text-align:center; display: block;\"><iframe loading=\"lazy\" class=\"youtube-player\" title=\"YouTube video player\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/_KDNv4yo0w0?version=3&#038;rel=1&#038;showsearch=0&#038;showinfo=1&#038;iv_load_policy=1&#038;fs=1&#038;hl=en-US&#038;autohide=2&#038;wmode=transparent\" allowfullscreen=\"true\" style=\"border:0;\" sandbox=\"allow-scripts allow-same-origin allow-popups allow-presentation allow-popups-to-escape-sandbox\"><\/iframe><\/span>\n<\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Zamba is one of the longest-running projects at DrivenData. You can read about it in this blog post: <a href=\"https:\/\/drivendata.co\/blog\/pjmf-zamba-conservation\">Computer vision for wildlife monitoring in a changing climate<\/a>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">And if you want to know more about my part of it, I wrote this series of articles.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/drivendata.co\/blog\/zamba-remove-blanks\">You can stop watching blank videos<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/drivendata.co\/blog\/zamba-target-search\">Find all the pangolins<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.drivendata.co\/blog\/zamba-choose-threshold\">Standing on the threshold<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/drivendata.co\/blog\/zamba-find-takahe\">What\u2019s a takahe?<\/a><\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Most recently, I&#8217;ve been working on calibrating the predictions from convolutional neural networks (CNNs). I haven&#8217;t written about it, but at ODSC East 2023, I&#8217;m giving a talk about it:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"wp-block-paragraph\"><strong>Don\u2019t Discard That Pangolin, Calibrate Your Deep Learning Classifier\u00a0<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>Suppose you are an ecologist studying a rare species like a pangolin. You can use motion-triggered camera traps to collect data about the presence and abundance of species in the wild, but for every video showing a pangolin, you have 100 that show other species, and 100 more that are blank. You might have to watch hours of video to find one pangolin.<\/em><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>Deep learning can help. <a href=\"https:\/\/zamba.drivendata.org\">Project Zamba<\/a> provides models that classify camera trap videos and identify the species that appear in them. Of course, the results are not perfect, but we can often remove 80% of the videos we don\u2019t want while losing only 10-20% of the videos we want.<\/em><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>But there\u2019s a problem. The output from deep learning classifiers is generally a \u201cconfidence score\u201d, not a probability. If a classifier assigns a label with 80% confidence, that doesn\u2019t mean there is an 80% chance it is correct. However, with a modest number of human-generated labels, we can often calibrate the output to produce more accurate probabilities, and make better predictions.<\/em><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>In this talk, I\u2019ll present use cases based on data from Africa, Guam, and New Zealand, and show how we can use deep learning and calibration to save the pangolin\u2026 or at least the pangolin videos. This real-world problem shows how users of ML models can tune the results to improve performance on their applications.\u00a0\u00a0<\/em><\/p>\n<\/blockquote>\n\n\n\n<p class=\"wp-block-paragraph\"> The ODSC schedule isn&#8217;t posted yet, but I&#8217;ll fill in the details later.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Sadly, today is my last day at DrivenData, so it&#8217;s a good time to review one of the projects I&#8217;ve been working on, using probabilistic predictions from Zamba to find animals in camera trap videos, like this: Zamba is one of the longest-running projects at DrivenData. You can read about it in this blog post: Computer vision for wildlife monitoring in a changing climate. And if you want to know more about my part of it, I wrote this series&#8230;<\/p>\n<p class=\"read-more\"><a class=\"btn btn-default\" href=\"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/\"> Read More<span class=\"screen-reader-text\">  Read More<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_hide_featured_image":false,"_jetpack_featured_image_duplicate_dismissed":0,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"jetpack_post_was_ever_published":false},"categories":[1],"tags":[],"class_list":["post-855","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Don&#039;t discard that pangolin - Probably Overthinking It<\/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.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Don&#039;t discard that pangolin - Probably Overthinking It\" \/>\n<meta property=\"og:description\" content=\"Sadly, today is my last day at DrivenData, so it&#8217;s a good time to review one of the projects I&#8217;ve been working on, using probabilistic predictions from Zamba to find animals in camera trap videos, like this: Zamba is one of the longest-running projects at DrivenData. You can read about it in this blog post: Computer vision for wildlife monitoring in a changing climate. And if you want to know more about my part of it, I wrote this series... Read More Read More\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/\" \/>\n<meta property=\"og:site_name\" content=\"Probably Overthinking It\" \/>\n<meta property=\"article:published_time\" content=\"2023-02-10T16:53:04+00:00\" \/>\n<meta name=\"author\" content=\"Allen B. Downey\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@AllenDowney\" \/>\n<meta name=\"twitter:site\" content=\"@AllenDowney\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Allen B. Downey\" \/>\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\":\"Article\",\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/\"},\"author\":{\"name\":\"Allen B. Downey\",\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/#\\\/schema\\\/person\\\/4e5bfb2e9af6c3446cb0031a7bf83207\"},\"headline\":\"Don&#8217;t discard that pangolin\",\"datePublished\":\"2023-02-10T16:53:04+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/\"},\"wordCount\":397,\"publisher\":{\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/#\\\/schema\\\/person\\\/4e5bfb2e9af6c3446cb0031a7bf83207\"},\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/\",\"url\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/\",\"name\":\"Don't discard that pangolin - Probably Overthinking It\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/#website\"},\"datePublished\":\"2023-02-10T16:53:04+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/2023\\\/02\\\/10\\\/dont-discard-that-pangolin\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Don&#8217;t discard that pangolin\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/\",\"name\":\"Probably Overthinking It\",\"description\":\"Data science, Bayesian Statistics, and other ideas\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/#\\\/schema\\\/person\\\/4e5bfb2e9af6c3446cb0031a7bf83207\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/#\\\/schema\\\/person\\\/4e5bfb2e9af6c3446cb0031a7bf83207\",\"name\":\"Allen B. Downey\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/probably_logo.png\",\"url\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/probably_logo.png\",\"contentUrl\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/probably_logo.png\",\"width\":714,\"height\":784,\"caption\":\"Allen B. Downey\"},\"logo\":{\"@id\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/probably_logo.png\"},\"sameAs\":[\"https:\\\/\\\/www.allendowney.com\\\/\",\"https:\\\/\\\/www.linkedin.com\\\/in\\\/allendowney\\\/\",\"https:\\\/\\\/x.com\\\/AllenDowney\",\"https:\\\/\\\/github.com\\\/AllenDowney\",\"https:\\\/\\\/bsky.app\\\/profile\\\/allendowney.bsky.social\",\"https:\\\/\\\/allendowney.github.io\\\/Portfolio\\\/\",\"https:\\\/\\\/greenteapress.com\\\/wp\\\/\"],\"url\":\"https:\\\/\\\/www.allendowney.com\\\/blog\\\/author\\\/allen-downey\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Don't discard that pangolin - Probably Overthinking It","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.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/","og_locale":"en_US","og_type":"article","og_title":"Don't discard that pangolin - Probably Overthinking It","og_description":"Sadly, today is my last day at DrivenData, so it&#8217;s a good time to review one of the projects I&#8217;ve been working on, using probabilistic predictions from Zamba to find animals in camera trap videos, like this: Zamba is one of the longest-running projects at DrivenData. You can read about it in this blog post: Computer vision for wildlife monitoring in a changing climate. And if you want to know more about my part of it, I wrote this series... Read More Read More","og_url":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/","og_site_name":"Probably Overthinking It","article_published_time":"2023-02-10T16:53:04+00:00","author":"Allen B. Downey","twitter_card":"summary_large_image","twitter_creator":"@AllenDowney","twitter_site":"@AllenDowney","twitter_misc":{"Written by":"Allen B. Downey","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/#article","isPartOf":{"@id":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/"},"author":{"name":"Allen B. Downey","@id":"https:\/\/www.allendowney.com\/blog\/#\/schema\/person\/4e5bfb2e9af6c3446cb0031a7bf83207"},"headline":"Don&#8217;t discard that pangolin","datePublished":"2023-02-10T16:53:04+00:00","mainEntityOfPage":{"@id":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/"},"wordCount":397,"publisher":{"@id":"https:\/\/www.allendowney.com\/blog\/#\/schema\/person\/4e5bfb2e9af6c3446cb0031a7bf83207"},"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/","url":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/","name":"Don't discard that pangolin - Probably Overthinking It","isPartOf":{"@id":"https:\/\/www.allendowney.com\/blog\/#website"},"datePublished":"2023-02-10T16:53:04+00:00","breadcrumb":{"@id":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.allendowney.com\/blog\/2023\/02\/10\/dont-discard-that-pangolin\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.allendowney.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Don&#8217;t discard that pangolin"}]},{"@type":"WebSite","@id":"https:\/\/www.allendowney.com\/blog\/#website","url":"https:\/\/www.allendowney.com\/blog\/","name":"Probably Overthinking It","description":"Data science, Bayesian Statistics, and other ideas","publisher":{"@id":"https:\/\/www.allendowney.com\/blog\/#\/schema\/person\/4e5bfb2e9af6c3446cb0031a7bf83207"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.allendowney.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/www.allendowney.com\/blog\/#\/schema\/person\/4e5bfb2e9af6c3446cb0031a7bf83207","name":"Allen B. Downey","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.allendowney.com\/blog\/wp-content\/uploads\/2025\/03\/probably_logo.png","url":"https:\/\/www.allendowney.com\/blog\/wp-content\/uploads\/2025\/03\/probably_logo.png","contentUrl":"https:\/\/www.allendowney.com\/blog\/wp-content\/uploads\/2025\/03\/probably_logo.png","width":714,"height":784,"caption":"Allen B. Downey"},"logo":{"@id":"https:\/\/www.allendowney.com\/blog\/wp-content\/uploads\/2025\/03\/probably_logo.png"},"sameAs":["https:\/\/www.allendowney.com\/","https:\/\/www.linkedin.com\/in\/allendowney\/","https:\/\/x.com\/AllenDowney","https:\/\/github.com\/AllenDowney","https:\/\/bsky.app\/profile\/allendowney.bsky.social","https:\/\/allendowney.github.io\/Portfolio\/","https:\/\/greenteapress.com\/wp\/"],"url":"https:\/\/www.allendowney.com\/blog\/author\/allen-downey\/"}]}},"jetpack_publicize_connections":[],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/posts\/855","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/comments?post=855"}],"version-history":[{"count":1,"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/posts\/855\/revisions"}],"predecessor-version":[{"id":856,"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/posts\/855\/revisions\/856"}],"wp:attachment":[{"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/media?parent=855"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/categories?post=855"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.allendowney.com\/blog\/wp-json\/wp\/v2\/tags?post=855"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}