{"id":26,"date":"2023-05-08T00:17:32","date_gmt":"2023-05-08T00:17:32","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/?page_id=26"},"modified":"2023-05-08T04:22:36","modified_gmt":"2023-05-08T04:22:36","slug":"spring-23-progress","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/","title":{"rendered":"Spring &#8217;23 Progress"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\">Resources<\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/docs.google.com\/presentation\/d\/1LwxAO5nKST9QtQUuwY5MIUkzivl-rVMlaIac-shDByM\/edit#slide=id.p\">Presentation slides<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/docs.google.com\/presentation\/d\/1uSfv_7XlwSvqN6mf8YECAG3HW3EMMUQKOFSSnor-BHM\/edit?usp=share_link\">Poster<\/a><\/li>\n<\/ul>\n\n\n\n<h4 class=\"wp-block-heading\">Model Diagnosis<\/h4>\n\n\n\n<h5 class=\"wp-block-heading\">HYPERPLAne OPtimization for attribute boundary<\/h5>\n\n\n\n<p>We are learning the behavior of the diffusion latent space and exploring both the h-space (bottleneck of U-Net) and e-space (image space) for attribute manipulation. We&#8217;ve tried to find the hyperplane that corresponds to a given attribute in h-space and\/or e-space. Below are some generated images as we traverse the normal vector to the discovered attribute hyperplane.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM.png\" alt=\"\" class=\"wp-image-111\" width=\"477\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM.png 610w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM-300x189.png 300w\" sizes=\"auto, (max-width: 477px) 100vw, 477px\" \/><\/figure>\n\n\n\n<p>As you see above, the attribute manipulation feels limited via this method of hyperplane traversal. One key challenge is that, since diffusion models have many steps, we can make edits to the latent vector in many ways: at one step only, at each step, same edit at each step, different edit per step, etc. My feeling is that we have not found the most optimal way to manipulate the diffusion latent vector for semantic edits.<\/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<p>Following the work above, training an implicit function would enable us to make step-dependent edits to the diffusion latent vector. The implicit function takes as input a step <em>s<\/em> and the h-space vector to produce <em>delta_h<\/em>, which is then added to the h-space vector in the bottleneck layer of U-Net. We&#8217;ve experimented with extending this idea to <strong>latent diffusion models<\/strong>, but the results are not convincing.<\/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\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"698\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.15.16-AM-1024x698.png\" alt=\"\" class=\"wp-image-112\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.15.16-AM-1024x698.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.15.16-AM-300x205.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.15.16-AM-768x524.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.15.16-AM.png 1044w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>In this line of work, we established a proof-of-concept by:<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li> First prompting GPT-4 to get relevant attributes for a given domain<\/li>\n\n\n\n<li>Query text2image to generate 100s of examples for each attribute from 1.<\/li>\n\n\n\n<li>Run a target model on these images to get a coarse sensitivity score<\/li>\n<\/ol>\n\n\n\n<p>The next steps would be to run a deeper sensitivity analysis using one of the frameworks HYPERPLANE OPTIMIZATION or IMPLICIT FUNCTION EDIT. <\/p>\n\n\n\n<h4 class=\"wp-block-heading\">Data Augmentation<\/h4>\n\n\n\n<p>Given the scarcity of data in medical AI, we have identified the medical domain as a primary area of focus for our research. Specifically, we aim to expand the widely-used VinDR-CXR dataset, which includes 15,000 accurately labeled chest X-ray images across 14 disease categories. However, the imbalanced distribution of images across these categories presents a challenge, as some disease classes have significantly fewer examples than others. To address this, we propose generating synthetic images for these underrepresented classes, and assessing the quality of these generated images through a comprehensive evaluation of downstream classification models trained on both synthetic and real images.<\/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=\"1024\" height=\"718\" data-id=\"96\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.40-1024x718.png\" alt=\"\" class=\"wp-image-96\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.40-1024x718.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.40-300x210.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.40-768x538.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.40.png 1298w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"741\" data-id=\"97\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.52-1024x741.png\" alt=\"\" class=\"wp-image-97\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.52-1024x741.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.52-300x217.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.52-768x555.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.04.52.png 1272w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p>We fine-tuned the Stable Diffusion 1.4v model with the DreamBooth approach, utilizing a small set of 3-5 images from each class within the target domain. Qualitatively, the generated images exhibit a noticeable improvement in resemblance to real images from the target domain.<\/p>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-2 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"332\" height=\"392\" data-id=\"98\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.34-1.png\" alt=\"\" class=\"wp-image-98\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.34-1.png 332w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.34-1-254x300.png 254w\" sizes=\"auto, (max-width: 332px) 100vw, 332px\" \/><figcaption class=\"wp-element-caption\">Target Image<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"366\" height=\"364\" data-id=\"100\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51-2.png\" alt=\"\" class=\"wp-image-100\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51-2.png 366w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51-2-300x298.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\uc804-10.44.51-2-150x150.png 150w\" sizes=\"auto, (max-width: 366px) 100vw, 366px\" \/><figcaption class=\"wp-element-caption\">Synthetic before fine-tuning<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"346\" height=\"350\" data-id=\"101\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.15.45.png\" alt=\"\" class=\"wp-image-101\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.15.45.png 346w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.15.45-297x300.png 297w\" sizes=\"auto, (max-width: 346px) 100vw, 346px\" \/><figcaption class=\"wp-element-caption\">Synthetic after fine-tuning<\/figcaption><\/figure>\n<\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p>In order to evaluate the quantitative impact of augmenting the dataset with synthetic images, we employed ResNet-50, pre-trained on ImageNet, to train a multi-label classification model on a four-class task. The synthetic images were generated to ensure even distribution of images for each class in the training dataset. We compared this method against three baseline approaches, including vanilla training with unbalanced classes, as well as under- and over-sampling methods with balanced classes. The quality of the generated images was assessed by measuring the performance of downstream classification models trained on these datasets.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"221\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.22.54-1024x221.png\" alt=\"\" class=\"wp-image-105\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.22.54-1024x221.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.22.54-300x65.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.22.54-768x166.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.22.54-1536x331.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.22.54.png 2030w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p>When compared to vanilla method, the DreamBooth Mix (synthetic image) achieves consistent improvements in all 4 lesions. It was also found to effectively address domain gaps in the majority classes, while undersampling led to a degradation in performance for these classes. Oversampling, on the other hand, resulted in no domain gaps between the training and added data, but was lacking in diversity. The approach will be further evaluated on more extreme cases, where only 5-20 real images are available for minority classes.<\/p>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-3 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"597\" data-id=\"107\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.43.34-1-1024x597.png\" alt=\"\" class=\"wp-image-107\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.43.34-1-1024x597.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.43.34-1-300x175.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.43.34-1-768x448.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.43.34-1.png 1214w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"597\" data-id=\"108\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.44.10-1024x597.png\" alt=\"\" class=\"wp-image-108\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.44.10-1024x597.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.44.10-300x175.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.44.10-768x448.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/\uc2a4\ud06c\ub9b0\uc0f7-2023-05-08-\uc624\ud6c4-12.44.10.png 1194w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<\/figure>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Resources Model Diagnosis HYPERPLAne OPtimization for attribute boundary We are learning the behavior of the diffusion latent space and exploring both the h-space (bottleneck of U-Net) and e-space (image space) for attribute manipulation. We&#8217;ve tried to find the hyperplane that corresponds to a given attribute in h-space and\/or e-space. Below are some generated images as [&hellip;]<\/p>\n","protected":false},"author":171,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-26","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>Spring &#039;23 Progress - 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\/spring-23-progress\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Spring &#039;23 Progress - Model Diagnosis with Domain Adaptation\" \/>\n<meta property=\"og:description\" content=\"Resources Model Diagnosis HYPERPLAne OPtimization for attribute boundary We are learning the behavior of the diffusion latent space and exploring both the h-space (bottleneck of U-Net) and e-space (image space) for attribute manipulation. We&#8217;ve tried to find the hyperplane that corresponds to a given attribute in h-space and\/or e-space. Below are some generated images as [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/\" \/>\n<meta property=\"og:site_name\" content=\"Model Diagnosis with Domain Adaptation\" \/>\n<meta property=\"article:modified_time\" content=\"2023-05-08T04:22:36+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM.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\\\/spring-23-progress\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/spring-23-progress\\\/\",\"name\":\"Spring '23 Progress - Model Diagnosis with Domain Adaptation\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/spring-23-progress\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/spring-23-progress\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/wp-content\\\/uploads\\\/sites\\\/87\\\/2023\\\/05\\\/Screen-Shot-2023-05-08-at-12.07.21-AM.png\",\"datePublished\":\"2023-05-08T00:17:32+00:00\",\"dateModified\":\"2023-05-08T04:22:36+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/spring-23-progress\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/spring-23-progress\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/spring-23-progress\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/wp-content\\\/uploads\\\/sites\\\/87\\\/2023\\\/05\\\/Screen-Shot-2023-05-08-at-12.07.21-AM.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/wp-content\\\/uploads\\\/sites\\\/87\\\/2023\\\/05\\\/Screen-Shot-2023-05-08-at-12.07.21-AM.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/spring-23-progress\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team10\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Spring &#8217;23 Progress\"}]},{\"@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":"Spring '23 Progress - 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\/spring-23-progress\/","og_locale":"en_US","og_type":"article","og_title":"Spring '23 Progress - Model Diagnosis with Domain Adaptation","og_description":"Resources Model Diagnosis HYPERPLAne OPtimization for attribute boundary We are learning the behavior of the diffusion latent space and exploring both the h-space (bottleneck of U-Net) and e-space (image space) for attribute manipulation. We&#8217;ve tried to find the hyperplane that corresponds to a given attribute in h-space and\/or e-space. Below are some generated images as [&hellip;]","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/","og_site_name":"Model Diagnosis with Domain Adaptation","article_modified_time":"2023-05-08T04:22:36+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM.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\/spring-23-progress\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/","name":"Spring '23 Progress - Model Diagnosis with Domain Adaptation","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM.png","datePublished":"2023-05-08T00:17:32+00:00","dateModified":"2023-05-08T04:22:36+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-content\/uploads\/sites\/87\/2023\/05\/Screen-Shot-2023-05-08-at-12.07.21-AM.png"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/spring-23-progress\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/"},{"@type":"ListItem","position":2,"name":"Spring &#8217;23 Progress"}]},{"@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\/26","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\/171"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/comments?post=26"}],"version-history":[{"count":9,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/pages\/26\/revisions"}],"predecessor-version":[{"id":113,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/pages\/26\/revisions\/113"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team10\/wp-json\/wp\/v2\/media?parent=26"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}