{"id":2,"date":"2023-05-01T17:46:21","date_gmt":"2023-05-01T17:46:21","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/?page_id=2"},"modified":"2023-05-08T03:03:00","modified_gmt":"2023-05-08T03:03:00","slug":"method-overview","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/","title":{"rendered":"Method Overview"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\"><strong>Model Diagnosis<\/strong><\/h4>\n\n\n\n<p>Given a target CV model of interest and a pretrained diffusion model, our goals for model diagnosis:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Can we evaluate the sensitivity of the target model to arbitrary visual attributes <strong>without a test set?<\/strong><\/li>\n\n\n\n<li>Better yet, can we discover relevant attributes in an <strong>unsupervised<\/strong> manner?<\/li>\n<\/ul>\n\n\n\n<p>Our work builds on the Zero-shot Model Diagnosis paper published in CVPR 2023 [4]. In this paper, the authors measure sensitivity of user given attributes using StyleGAN. We hope to extend this work by proposing a methodology that is completely unsupervised and that leverages the high expressive power of diffusion models.<\/p>\n\n\n\n<p>We are actively exploring three different approaches:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>#1: Hyperplane optimization for attribute boundary<\/li>\n\n\n\n<li>#2: Implicit function edit of diffusion h-space and\/or e-space<\/li>\n\n\n\n<li>#3: LLM-aided attribute discovery<\/li>\n<\/ul>\n\n\n\n<h5 class=\"wp-block-heading\">Hyperplane Optimization for attribute boundary<\/h5>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png\" alt=\"\" class=\"wp-image-91\" width=\"244\" height=\"210\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-300x259.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-768x662.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM.png 1390w\" sizes=\"auto, (max-width: 244px) 100vw, 244px\" \/><\/figure>\n\n\n\n<p>The key insight for this approach motivated by [1] and [3], where arbitrary attributes can be found in the latent space (of the generative model) through a hyperplane that separates the positive and negative examples. For our purpose, we want to optimize this hyperplane to find the most adversarial attributes given a target model.<\/p>\n\n\n\n<h5 class=\"wp-block-heading\">Implicit Function edit of diffusion h-space and\/or e-space<\/h5>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.35-PM-1024x635.png\" alt=\"\" class=\"wp-image-92\" width=\"334\" height=\"207\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.35-PM-1024x635.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.35-PM-300x186.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.35-PM-768x477.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.35-PM.png 1428w\" sizes=\"auto, (max-width: 334px) 100vw, 334px\" \/><\/figure>\n\n\n\n<p>This approach is motivated by [2], where the authors show that the latent space of diffusion models can be manipulated by training an implicit function to find the edit in the bottleneck layer of U-Net (delta_h). We want to build on this by training the implicit function to be adversarial.<\/p>\n\n\n\n<h5 class=\"wp-block-heading\">LLM-aided attribute Discovery <\/h5>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.51-PM-1024x597.png\" alt=\"\" class=\"wp-image-94\" width=\"325\" height=\"189\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.51-PM-1024x597.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.51-PM-300x175.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.51-PM-768x448.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.51-PM-1536x895.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.51-PM.png 1692w\" sizes=\"auto, (max-width: 325px) 100vw, 325px\" \/><\/figure>\n\n\n\n<p>While we hope to achieve purely unsupervised discovery of adversarial attributes, we recognize the difficulty in this goal and hope to hedge our bets by pursuing a parallel approach using LLMs for attribute discovery. In summary, we will prompt GPT-4 to output relevant attributes for some given domain, and feed these candidates to adversarial analysis downstream. <\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Data Augmentation<\/strong><\/h4>\n\n\n\n<p>In this research direction, we are trying to achieve the following goals:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Can we use targeted domain data generation to <strong>bridge the gap<\/strong> between the train and test image data domains?<\/li>\n\n\n\n<li>Better yet, can we address long-tail problems by leveraging synthetic images to <strong>augment scarce data?<\/strong><\/li>\n<\/ul>\n\n\n\n<p>To accomplish this, we are leveraging state-of-the-art text-to-image models, which have been trained on millions of images and can serve as a strong foundation for bridging the domain gap in a few-shot manner. <\/p>\n\n\n\n<p>However, off-the-shelf models that have not been fine-tuned on the target dataset may generate images that are not readily usable, as seen in the example of chest X-ray images below:<\/p>\n\n\n\n<p class=\"has-text-align-center\"><em>Prompt: &#8220;A photo of a lung x-ray&#8221;<\/em><\/p>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-1 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"332\" height=\"392\" data-id=\"67\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.34.png\" alt=\"\" class=\"wp-image-67\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.34.png 332w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.34-254x300.png 254w\" sizes=\"auto, (max-width: 332px) 100vw, 332px\" \/><figcaption class=\"wp-element-caption\"><strong>A target X-ray Image<\/strong><\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"366\" height=\"364\" data-id=\"68\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51.png\" alt=\"\" class=\"wp-image-68\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51.png 366w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51-300x298.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51-150x150.png 150w\" sizes=\"auto, (max-width: 366px) 100vw, 366px\" \/><figcaption class=\"wp-element-caption\"><strong>A synthetic X-ray Image<\/strong><\/figcaption><\/figure>\n<\/figure>\n\n\n\n<p>Therefore, we are actively exploring multiple approaches based on two recent related works that achieve personalization in a few-shot manner (<a href=\"https:\/\/arxiv.org\/abs\/2208.01618\">Gal et al. 2022<\/a>, <a href=\"https:\/\/arxiv.org\/abs\/2208.12242\">Ruiz et al. 2022<\/a>).<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Method 1: Hierarchical textual inversion<\/li>\n<\/ul>\n\n\n\n<p>This involves expanding textual inversion to employ multiple tokens in a hierarchical fashion. <\/p>\n\n\n\n<p>This two-step methodology can be adopted whereby a representation capable of bridging the gap in chest X-ray image generation is initially acquired as the primary task, followed by a secondary and more granular task of developing a separate representation that concentrates solely on generating specific diseases in the chest X-rays.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1008\" height=\"420\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-11.03.43.png\" alt=\"\" class=\"wp-image-79\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-11.03.43.png 1008w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-11.03.43-300x125.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-11.03.43-768x320.png 768w\" sizes=\"auto, (max-width: 1008px) 100vw, 1008px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Method 2: Prompt-assisted generation<\/li>\n<\/ul>\n\n\n\n<p>This involves constructing prompts that explicitly furnish the specifics of the target domain via text. For instance, in the case of chest X-rays, suppose we wish to produce images with pleural effusion. Rather than generating images using a straightforward prompt such as &#8220;A lung x-ray with pleural effusion&#8221;, we can incorporate more explicit visual characteristics such as &#8220;A lung x-ray with perihilar ground-glass opacities, peribronchial thickening, and interstitial and alveolar opacities in the mid to lower\u2026&#8221;, where these characteristics can be automatically extracted from models like ChatGPT.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">References<\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li>[1] <a href=\"https:\/\/arxiv.org\/abs\/2302.08357\" target=\"_blank\" rel=\"noreferrer noopener\">Ye Zhu et al. Boundary Guided Mixing Trajectory for Semantic Control with Diffusion Models<\/a><\/li>\n\n\n\n<li>[2] <a href=\"https:\/\/arxiv.org\/abs\/2210.10960\" target=\"_blank\" rel=\"noreferrer noopener\">Mingi Kwon et al. Diffusion Models already have a Semantic Latent Space<\/a><\/li>\n\n\n\n<li>[3] <a href=\"https:\/\/arxiv.org\/abs\/2104.14556\" target=\"_blank\" rel=\"noreferrer noopener\">Zhiheng et al. Discover the Unknown Biased Attribute of an Image Classifier<\/a><\/li>\n\n\n\n<li>[4] <a href=\"https:\/\/arxiv.org\/abs\/2303.15441\" target=\"_blank\" rel=\"noreferrer noopener\">Jinqi Luo et al. Zero-shot Model Diagnosis<\/a><\/li>\n<\/ul>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Model Diagnosis Given a target CV model of interest and a pretrained diffusion model, our goals for model diagnosis: Our work builds on the Zero-shot Model Diagnosis paper published in CVPR 2023 [4]. In this paper, the authors measure sensitivity of user given attributes using StyleGAN. We hope to extend this work by proposing a [&hellip;]<\/p>\n","protected":false},"author":172,"featured_media":0,"parent":0,"menu_order":1,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-2","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Method Overview - Model Diagnosis with Domain Adaptation<\/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:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Method Overview - Model Diagnosis with Domain Adaptation\" \/>\n<meta property=\"og:description\" content=\"Model Diagnosis Given a target CV model of interest and a pretrained diffusion model, our goals for model diagnosis: Our work builds on the Zero-shot Model Diagnosis paper published in CVPR 2023 [4]. In this paper, the authors measure sensitivity of user given attributes using StyleGAN. We hope to extend this work by proposing a [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/\" \/>\n<meta property=\"og:site_name\" content=\"Model Diagnosis with Domain Adaptation\" \/>\n<meta property=\"article:modified_time\" content=\"2023-05-08T03:03:00+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/\",\"name\":\"Method Overview - Model Diagnosis with Domain Adaptation\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/wp-content\\\/uploads\\\/sites\\\/87\\\/2023\\\/05\\\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png\",\"datePublished\":\"2023-05-01T17:46:21+00:00\",\"dateModified\":\"2023-05-08T03:03:00+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/wp-content\\\/uploads\\\/sites\\\/87\\\/2023\\\/05\\\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/wp-content\\\/uploads\\\/sites\\\/87\\\/2023\\\/05\\\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/method-overview\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Method Overview\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/\",\"name\":\"Model Diagnosis with Domain Adaptation\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Method Overview - Model Diagnosis with Domain Adaptation","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:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/","og_locale":"en_US","og_type":"article","og_title":"Method Overview - Model Diagnosis with Domain Adaptation","og_description":"Model Diagnosis Given a target CV model of interest and a pretrained diffusion model, our goals for model diagnosis: Our work builds on the Zero-shot Model Diagnosis paper published in CVPR 2023 [4]. In this paper, the authors measure sensitivity of user given attributes using StyleGAN. We hope to extend this work by proposing a [&hellip;]","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/","og_site_name":"Model Diagnosis with Domain Adaptation","article_modified_time":"2023-05-08T03:03:00+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/","name":"Method Overview - Model Diagnosis with Domain Adaptation","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png","datePublished":"2023-05-01T17:46:21+00:00","dateModified":"2023-05-08T03:03:00+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-07-at-11.02.19-PM-1024x883.png"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/method-overview\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/"},{"@type":"ListItem","position":2,"name":"Method Overview"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/","name":"Model Diagnosis with Domain Adaptation","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/pages\/2","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/users\/172"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/comments?post=2"}],"version-history":[{"count":10,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/pages\/2\/revisions"}],"predecessor-version":[{"id":95,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/pages\/2\/revisions\/95"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/media?parent=2"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}