{"id":2776112,"date":"2025-05-13T10:00:01","date_gmt":"2025-05-13T17:00:01","guid":{"rendered":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&#038;p=2776112"},"modified":"2025-05-13T10:55:15","modified_gmt":"2025-05-13T17:55:15","slug":"whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5","status":"publish","type":"blog","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5","title":{"rendered":"What&#8217;s new for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension"},"author":254042,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"open","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_searchwp_excluded":""},"categories":[770712,22931],"tags":[758311,174212,186132,779262,777242],"industry":[],"product":[36561],"class_list":["post-2776112","blog","type-blog","status-publish","format-standard","hentry","category-geoai","category-imagery","tag-ai","tag-artificial-intelligence","tag-deep-learning","tag-explainable-ai","tag-whats-new-in-arcgis-pro","product-arcgis-pro"],"acf":{"short_description":"ArcGIS Pro 3.5 helps you better explain feature classification, compute accuracy for pixel classification, and more.","flexible_content":[{"acf_fc_layout":"content","content":"<p><span data-teams=\"true\">Take advantage of powerful GeoAI capabilities in the ArcGIS Pro 3.5 Image Analyst extension. <\/span>With this release, you can now do the following:<\/p>\n<ul>\n<li>Explain object classification results better<\/li>\n<li>Assess pixel classification accuracy<\/li>\n<li>Monitor the model training <span data-olk-copy-source=\"MessageBody\">process <\/span>using TensorBoard<\/li>\n<li>Utilize a new object detection model type<\/li>\n<\/ul>\n<p>Discover how our latest features will streamline your workflows and boost your productivity.<\/p>\n"},{"acf_fc_layout":"content","content":"<h2>Explainable AI: Understanding object classification models with Grad-CAM<\/h2>\n<p>We&#8217;ve added support for Gradient-weighted Class Activation Mapping (Grad-CAM) for the <a href=\"https:\/\/pro.arcgis.com\/en\/pro-app\/latest\/help\/analysis\/image-analyst\/classify-objects.htm\" target=\"_blank\" rel=\"noopener\">object classification<\/a> deep learning workflows. This technique calculates the gradient of the most dominant logit with respect to the latest activation map, highlighting the most influential pixels in the image classification. When Grad-CAM support is enabled in the model definition, each feature in the output feature class now includes an attachment showing these influential pixels. This allows users to gain a better understanding of how the model makes decisions.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2777552,"id":2777552,"title":"Grad-CAM explanations for damaged structure classifications are shown. Yellow pixels indicate the highest influence on the model's decision, followed by red.","filename":"Grad-CAM2.png","filesize":650063,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\/grad-cam2","alt":"Grad-CAM highlights areas influencing damage classification: yellow for highest, then red.","author":"254042","description":"Grad-CAM explanations for damaged structure classifications are shown. Yellow pixels indicate the highest influence on the model's decision, followed by red.","caption":"Grad-CAM explanations for damaged structure classifications are shown. Yellow pixels indicate the highest influence on the model's decision, followed by red.","name":"grad-cam2","status":"inherit","uploaded_to":2776112,"date":"2025-04-29 16:48:13","modified":"2025-04-29 17:10:02","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":791,"height":638,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2.png","medium-width":324,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2.png","medium_large-width":768,"medium_large-height":619,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2.png","large-width":791,"large-height":638,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2.png","1536x1536-width":791,"1536x1536-height":638,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2.png","2048x2048-width":791,"2048x2048-height":638,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2-577x465.png","card_image-width":577,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Grad-CAM2.png","wide_image-width":791,"wide_image-height":638}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"<h2>Compute Accuracy For Pixel Classification<\/h2>\n<p>The new <a href=\"https:\/\/pro.arcgis.com\/en\/pro-app\/latest\/tool-reference\/image-analyst\/compute-accuracy-for-pixel-classification.htm\" target=\"_blank\" rel=\"noopener\">Compute Accuracy For Pixel Classification<\/a> tool evaluates the accuracy of pixel classification results from the <a href=\"https:\/\/pro.arcgis.com\/en\/pro-app\/latest\/tool-reference\/image-analyst\/classify-pixels-using-deep-learning.htm\" target=\"_blank\" rel=\"noopener\">Classify Pixels Using Deep Learning<\/a> tool. It computes a confusion matrix based on omission and commission errors, and the Intersection over Union (IoU) score by comparing the output of the Classify Pixels Using Deep Learning tool with ground truth data.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2776202,"id":2776202,"title":"Part of the accuracy report on the left, and the interface of the Compute Accuracy For Pixel Classification tool on the right.","filename":"Compute-Accuracy-For-Pixel-Classification.png","filesize":81275,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\/compute-accuracy-for-pixel-classification","alt":"The left side shows a portion of the accuracy report, while the right displays the Compute Accuracy For Pixel Classification tool interface.","author":"254042","description":"Part of the accuracy report on the left, and the interface of the Compute Accuracy For Pixel Classification tool on the right.","caption":"Part of the accuracy report on the left, and the interface of the Compute Accuracy For Pixel Classification tool on the right.","name":"compute-accuracy-for-pixel-classification","status":"inherit","uploaded_to":2776112,"date":"2025-04-29 00:12:46","modified":"2025-04-29 17:10:30","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":779,"height":325,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","medium-width":464,"medium-height":194,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","medium_large-width":768,"medium_large-height":320,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","large-width":779,"large-height":325,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","1536x1536-width":779,"1536x1536-height":325,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","2048x2048-width":779,"2048x2048-height":325,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","card_image-width":779,"card_image-height":325,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/Compute-Accuracy-For-Pixel-Classification.png","wide_image-width":779,"wide_image-height":325}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"<h2>TensorBoard integration in the Train Deep Learning Tool and Training Wizard<\/h2>\n<p>The <a href=\"https:\/\/pro.arcgis.com\/en\/pro-app\/latest\/tool-reference\/image-analyst\/train-deep-learning-model.htm\">Train Deep Learning<\/a> tool and the <a href=\"https:\/\/pro.arcgis.com\/en\/pro-app\/latest\/help\/analysis\/image-analyst\/train-deep-learning-model-wizard.htm\" target=\"_blank\" rel=\"noopener\">Training wizard<\/a> on the Imagery tab now include TensorBoard integration. This integration enables you to monitor the model training process. Selecting the &#8216;Enable TensorBoard&#8217; option displays a TensorBoard dashboard, offering a visual representation of training logs. TensorBoard is a toolkit for visualizing training progress, displaying logs as graphs, images, histograms, and other data. This feature supports various models such as CycleGAN, DeepLab, and more. For additional details and the complete list of supported models, refer to <a href=\"https:\/\/developers.arcgis.com\/python\/latest\/guide\/monitor-model-training-with-tensorboard\/\" target=\"_blank\" rel=\"noopener\">What is TensorBoard?<\/a><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2776172,"id":2776172,"title":"Example of the TensorBoard interface and reports","filename":"tensorboard.png","filesize":275536,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\/tensorboard","alt":"TensorBoard interface","author":"254042","description":"Example of the TensorBoard interface and reports","caption":"Example of the TensorBoard interface and reports","name":"tensorboard","status":"inherit","uploaded_to":2776112,"date":"2025-04-29 00:07:28","modified":"2025-05-08 19:53:03","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":3576,"height":1743,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard.png","medium-width":464,"medium-height":226,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard.png","medium_large-width":768,"medium_large-height":374,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard.png","large-width":1920,"large-height":936,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard-1536x749.png","1536x1536-width":1536,"1536x1536-height":749,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard-2048x998.png","2048x2048-width":2048,"2048x2048-height":998,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard-826x403.png","card_image-width":826,"card_image-height":403,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/tensorboard-1920x936.png","wide_image-width":1920,"wide_image-height":936}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"<h2>New RTDetrV2 object detection model type<\/h2>\n<p>ArcGIS Pro 3.5 introduces the <a href=\"https:\/\/arxiv.org\/abs\/2407.17140\" target=\"_blank\" rel=\"noopener\">RTDetrV2<\/a> model architecture for object detection. RTDETRV2 is built upon the architecture of <a href=\"https:\/\/arxiv.org\/abs\/2304.08069\" target=\"_blank\" rel=\"noopener\">RT-DETR<\/a>, which is an object detection model that stands for \u201cReal-Time DEtection Transformer.\u201d This model is designed to perform object detection tasks with a focus on achieving real-time performance while maintaining high accuracy. RTDetrV2 provides selective multi-scale feature extraction in the decoder, and an optional discrete sampling operator, which makes the model easier to deploy on various hardware by removing certain technical limitations without sacrificing detection accuracy.<\/p>\n"},{"acf_fc_layout":"content","content":"<h2>Wrap-up<\/h2>\n<p>These updates for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension now provide you with new and enhanced tools for better understanding and control of your deep learning workflows. We hope these features will contribute to more effective and informative image analysis.<\/p>\n"}],"show_article_image":false,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/04\/card2.png","wide_image":false,"authors":[{"ID":254042,"user_firstname":"Pavan","user_lastname":"Yadav","nickname":"Pavan Yadav","user_nicename":"pyadav","display_name":"Pavan Yadav","user_email":"PYadav@esri.com","user_url":"","user_registered":"2021-07-20 16:55:01","user_description":"Pavan Yadav is a Senior Software Product Engineer at Esri's Imagery team, leveraging AI to extract valuable insights from imagery data and contributing to the development of geospatial AI (GeoAI).","user_avatar":"<img data-del=\"avatar\" src='https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/12\/Pavan-Yadav-213x200.jpg' class='avatar pp-user-avatar avatar-96 photo ' height='96' width='96'\/>"}],"related_articles":[{"ID":2585592,"post_author":"254042","post_date":"2024-11-19 00:01:50","post_date_gmt":"2024-11-19 08:01:50","post_content":"","post_title":"What's new for GeoAI in the Image Analyst extension of ArcGIS Pro 3.4","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-4","to_ping":"","pinged":"","post_modified":"2024-11-19 01:38:39","post_modified_gmt":"2024-11-19 09:38:39","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&#038;p=2585592","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"2","filter":"raw"},{"ID":2318532,"post_author":"254042","post_date":"2024-05-09 00:01:49","post_date_gmt":"2024-05-09 07:01:49","post_content":"","post_title":"What's new for GeoAI in the Image Analyst extension of ArcGIS Pro 3.3","post_excerpt":"","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-3","to_ping":"","pinged":"","post_modified":"2024-05-14 11:12:58","post_modified_gmt":"2024-05-14 18:12:58","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&#038;p=2318532","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":2090062,"post_author":"254042","post_date":"2023-11-14 00:00:09","post_date_gmt":"2023-11-14 08:00:09","post_content":"","post_title":"Deep Learning for Image Analyst \u2013 What\u2019s New in ArcGIS Pro 3.2","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"deep-learning-for-image-analyst-whats-new-in-arcgis-pro-3-2","to_ping":"","pinged":"","post_modified":"2023-12-04 15:24:43","post_modified_gmt":"2023-12-04 23:24:43","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&#038;p=2090062","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":1302112,"post_author":"178852","post_date":"2021-08-02 11:56:22","post_date_gmt":"2021-08-02 18:56:22","post_content":"","post_title":"Performing Feature Extraction &amp; Classification Using Deep Learning with ArcGIS Pro","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"performing-feature-extraction-classification-using-deep-learning-with-arcgis-pro","to_ping":"","pinged":"","post_modified":"2022-08-25 13:59:34","post_modified_gmt":"2022-08-25 20:59:34","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&#038;p=1302112","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"1","filter":"raw"},{"ID":1956882,"post_author":"254042","post_date":"2023-06-14 06:00:09","post_date_gmt":"2023-06-14 13:00:09","post_content":"","post_title":"Repurposing Deep Learning Models using Transfer Learning in ArcGIS","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"repurposing-deep-learning-models-using-transfer-learning-in-arcgis","to_ping":"","pinged":"","post_modified":"2023-07-17 10:30:58","post_modified_gmt":"2023-07-17 17:30:58","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&#038;p=1956882","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"3","filter":"raw"},{"ID":1319782,"post_author":"254042","post_date":"2021-08-23 17:33:26","post_date_gmt":"2021-08-24 00:33:26","post_content":"","post_title":"Colorizing Historic Black and White Aerial Imagery using Deep Learning","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"colorizing-historic-black-and-white-aerial-imagery-using-deep-learning","to_ping":"","pinged":"","post_modified":"2022-01-13 15:04:59","post_modified_gmt":"2022-01-13 23:04:59","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&#038;p=1319782","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"}]},"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.9 (Yoast SEO v25.9) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>GeoAI in ArcGIS Pro 3.5 Image Analyst<\/title>\n<meta name=\"description\" content=\"Imagery GeoAI in ArcGIS Pro 3.5: Grad-CAM, pixel classification assessments, TensorBoard monitoring, a new model type.\" \/>\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.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"What&#039;s new for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension\" \/>\n<meta property=\"og:description\" content=\"Imagery GeoAI in ArcGIS Pro 3.5: Grad-CAM, pixel classification assessments, TensorBoard monitoring, a new model type.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\" \/>\n<meta property=\"og:site_name\" content=\"ArcGIS Blog\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/esrigis\/\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-13T17:55:15+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@ESRI\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":[\"Article\",\"BlogPosting\"],\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\"},\"author\":{\"name\":\"Pavan Yadav\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/17827d4b26faea91d7d4c478ab8e5333\"},\"headline\":\"What&#8217;s new for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension\",\"datePublished\":\"2025-05-13T17:00:01+00:00\",\"dateModified\":\"2025-05-13T17:55:15+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\"},\"wordCount\":12,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"keywords\":[\"AI\",\"Artificial Intelligence\",\"deep learning\",\"Explainable AI\",\"What's new in ArcGIS Pro\"],\"articleSection\":[\"AI\",\"Imagery &amp; Remote Sensing\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\",\"name\":\"GeoAI in ArcGIS Pro 3.5 Image Analyst\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\"},\"datePublished\":\"2025-05-13T17:00:01+00:00\",\"dateModified\":\"2025-05-13T17:55:15+00:00\",\"description\":\"Imagery GeoAI in ArcGIS Pro 3.5: Grad-CAM, pixel classification assessments, TensorBoard monitoring, a new model type.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.esri.com\/arcgis-blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"What&#8217;s new for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/\",\"name\":\"ArcGIS Blog\",\"description\":\"Get insider info from Esri product teams\",\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.esri.com\/arcgis-blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\",\"name\":\"Esri\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png\",\"contentUrl\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png\",\"width\":400,\"height\":400,\"caption\":\"Esri\"},\"image\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/esrigis\/\",\"https:\/\/x.com\/ESRI\",\"https:\/\/www.linkedin.com\/company\/5311\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/17827d4b26faea91d7d4c478ab8e5333\",\"name\":\"Pavan Yadav\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/12\/Pavan-Yadav-213x200.jpg\",\"contentUrl\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/12\/Pavan-Yadav-213x200.jpg\",\"caption\":\"Pavan Yadav\"},\"description\":\"Pavan Yadav is a Senior Software Product Engineer at Esri's Imagery team, leveraging AI to extract valuable insights from imagery data and contributing to the development of geospatial AI (GeoAI).\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/pavan-yadav-1846606\/\"],\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/author\/pyadav\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"GeoAI in ArcGIS Pro 3.5 Image Analyst","description":"Imagery GeoAI in ArcGIS Pro 3.5: Grad-CAM, pixel classification assessments, TensorBoard monitoring, a new model type.","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.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5","og_locale":"en_US","og_type":"article","og_title":"What's new for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension","og_description":"Imagery GeoAI in ArcGIS Pro 3.5: Grad-CAM, pixel classification assessments, TensorBoard monitoring, a new model type.","og_url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5","og_site_name":"ArcGIS Blog","article_publisher":"https:\/\/www.facebook.com\/esrigis\/","article_modified_time":"2025-05-13T17:55:15+00:00","twitter_card":"summary_large_image","twitter_site":"@ESRI","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":["Article","BlogPosting"],"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#article","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5"},"author":{"name":"Pavan Yadav","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/17827d4b26faea91d7d4c478ab8e5333"},"headline":"What&#8217;s new for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension","datePublished":"2025-05-13T17:00:01+00:00","dateModified":"2025-05-13T17:55:15+00:00","mainEntityOfPage":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5"},"wordCount":12,"commentCount":0,"publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"keywords":["AI","Artificial Intelligence","deep learning","Explainable AI","What's new in ArcGIS Pro"],"articleSection":["AI","Imagery &amp; Remote Sensing"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5","url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5","name":"GeoAI in ArcGIS Pro 3.5 Image Analyst","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#website"},"datePublished":"2025-05-13T17:00:01+00:00","dateModified":"2025-05-13T17:55:15+00:00","description":"Imagery GeoAI in ArcGIS Pro 3.5: Grad-CAM, pixel classification assessments, TensorBoard monitoring, a new model type.","breadcrumb":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/whats-new-for-geoai-in-the-image-analyst-extension-of-arcgis-pro-3-5#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.esri.com\/arcgis-blog\/"},{"@type":"ListItem","position":2,"name":"What&#8217;s new for GeoAI in the ArcGIS Pro 3.5 Image Analyst extension"}]},{"@type":"WebSite","@id":"https:\/\/www.esri.com\/arcgis-blog\/#website","url":"https:\/\/www.esri.com\/arcgis-blog\/","name":"ArcGIS Blog","description":"Get insider info from Esri product teams","publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.esri.com\/arcgis-blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization","name":"Esri","url":"https:\/\/www.esri.com\/arcgis-blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png","contentUrl":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png","width":400,"height":400,"caption":"Esri"},"image":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/esrigis\/","https:\/\/x.com\/ESRI","https:\/\/www.linkedin.com\/company\/5311\/"]},{"@type":"Person","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/17827d4b26faea91d7d4c478ab8e5333","name":"Pavan Yadav","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/","url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/12\/Pavan-Yadav-213x200.jpg","contentUrl":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/12\/Pavan-Yadav-213x200.jpg","caption":"Pavan Yadav"},"description":"Pavan Yadav is a Senior Software Product Engineer at Esri's Imagery team, leveraging AI to extract valuable insights from imagery data and contributing to the development of geospatial AI (GeoAI).","sameAs":["https:\/\/www.linkedin.com\/in\/pavan-yadav-1846606\/"],"url":"https:\/\/www.esri.com\/arcgis-blog\/author\/pyadav"}]}},"text_date":"May 13, 2025","author_name":"Pavan Yadav","author_page":"https:\/\/www.esri.com\/arcgis-blog\/author\/pyadav","custom_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/08\/Newsroom-Keyart-Wide-1920-x-1080.jpg","primary_product":"ArcGIS Pro","tag_data":[{"term_id":758311,"name":"AI","slug":"ai","term_group":0,"term_taxonomy_id":758311,"taxonomy":"post_tag","description":"","parent":0,"count":29,"filter":"raw"},{"term_id":174212,"name":"Artificial Intelligence","slug":"artificial-intelligence","term_group":0,"term_taxonomy_id":174212,"taxonomy":"post_tag","description":"","parent":0,"count":22,"filter":"raw"},{"term_id":186132,"name":"deep learning","slug":"deep-learning","term_group":0,"term_taxonomy_id":186132,"taxonomy":"post_tag","description":"","parent":0,"count":65,"filter":"raw"},{"term_id":779262,"name":"Explainable AI","slug":"explainable-ai","term_group":0,"term_taxonomy_id":779262,"taxonomy":"post_tag","description":"","parent":0,"count":1,"filter":"raw"},{"term_id":777242,"name":"What's new in ArcGIS Pro","slug":"whats-new-in-arcgis-pro","term_group":0,"term_taxonomy_id":777242,"taxonomy":"post_tag","description":"","parent":0,"count":2,"filter":"raw"}],"category_data":[{"term_id":770712,"name":"AI","slug":"geoai","term_group":0,"term_taxonomy_id":770712,"taxonomy":"category","description":"","parent":0,"count":51,"filter":"raw"},{"term_id":22931,"name":"Imagery &amp; Remote Sensing","slug":"imagery","term_group":0,"term_taxonomy_id":22931,"taxonomy":"category","description":"","parent":0,"count":765,"filter":"raw"}],"product_data":[{"term_id":36561,"name":"ArcGIS Pro","slug":"arcgis-pro","term_group":0,"term_taxonomy_id":36561,"taxonomy":"product","description":"","parent":0,"count":2035,"filter":"raw"}],"primary_product_link":"https:\/\/www.esri.com\/arcgis-blog\/?s=#&products=arcgis-pro","_links":{"self":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/2776112","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog"}],"about":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/types\/blog"}],"author":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/users\/254042"}],"replies":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/comments?post=2776112"}],"version-history":[{"count":0,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/2776112\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/media?parent=2776112"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/categories?post=2776112"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/tags?post=2776112"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/industry?post=2776112"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/product?post=2776112"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}