[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-267352-105":59,"doc-detail-267352-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","deep-visual-analogy-making-paper","Deep Visual Analogy-Making - Paper","","Image understanding depends not only on recognizing content within a single image, but also on relating images and producing corresponding new images. This paper presents an end-to-end deep network for visual analogy making, transforming a query image using an example pair. The method learns an embedding that supports analogical reasoning through vector-based operations, then decodes transformed embeddings back to the image space. Experiments validate results on 2D shapes, animated sprites, and 3D car models.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/deep-visual-analogy-making-paper/267352/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/deep-visual-analogy-making-paper/267352.png","ImageObject",300,407,{"name":92,"@type":93},"Dipper","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-09","2026-09-14",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is visual analogy making in this paper?","Question",{"text":113,"@type":114},"It transforms a query image using an example pair of related images, producing a completed analogy image.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the model perform analogical reasoning?",{"text":118,"@type":114},"It maps images into an embedding space where analogies are carried out with operations such as vector subtraction and addition, then applies a decoder to generate the transformed image.",{"name":120,"@type":111,"acceptedAnswer":121},"What datasets and tasks are used to evaluate the approach?",{"text":122,"@type":114},"The paper evaluates visual analogy completion on 2D shapes, demonstrates animation transfer and analogy traversal on animated game sprites, and applies pose/rotation transfer on 3D car models.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},267352,1789417523,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":144,"preview_page_count":4},1374404997633,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Deep Visual Analogy-Making  \nScott Reed Yi Zhang Yuting Zhang Honglak Lee  \nUniversity of Michigan, Ann Arbor, MI 48109, USA freedscot,yeezhang,yutingzh,[honglak](honglakg@umich.edu)[g](honglakg@umich.edu)[@umich.edu](honglakg@umich.edu)  \nAbstract  \nIn addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding. Recently, deep convolutional networks have yielded breakthroughs in predicting image labels, annotations and captions, but have only just begun to be used for generating high-quality images. In this paper we develop a novel deep network trained end-to-end to perform visual analogy making, which is the task of transforming a query image according to an example pair of related images. Solving this problem requires both accurately recognizing a visual relationship and generating a transformed query image accordingly. Inspired by recent advances in language modeling, we propose to solve visual analogies by learning to map images to a neural embedding in which analogical reasoning is simple, such as by vector subtraction and addition. In experiments, our model effectively models visual analogies on several datasets: 2D shapes, animated video game sprites, and 3D car models.  \n1 Introduction  \nHumans are good at considering “what-if?” questions about objects in their environment. What if this chair were rotated 30 degrees clockwise? What if I dyed my hair blue? We can easily imagine roughly how objects would look according to various hypothetical questions. However, current generative models of images struggle to perform this kind of task without encoding significant prior knowledge about the environment and restricting the allowed transformations.  \nOften, these visual hypothetical questions can be effectively answered by analogical reasoning.1 Having observed many similar objects rotating, one could learn to mentally rotate new objects. Having observed objects with different colors (or textures), one could learn to mentally recolor (or re-texture) new objects.  \nSolving the analogy problem requires the ability to identify relationships among images and transform query images accord-  \nFigure 1: Visual analogy making concept. We learn an encoder function f mapping images into a space in which analogies can be performed, and a decoderg mapping back to the image space.  \ningly. In this paper, we propose to solve the problem by directly training on visual analogy completion; that is, to generate the transformed image output. Note that we do not make any claim about how humans solve the problem, but we show that in many cases thinking by analogy is enough to solve it, without exhaustively encoding first principles into a complex model.  \nWe denote a valid analogy as a 4-tuple A : B :: C : D, often spoken as “A is to B as C is to D”. Given such an analogy, there are several questions one might ask:  \n􀀏 A ? B :: C ? D-What is the common relationship?  \n􀀏 A : B ? C : D-Are A and B related in the same way that C and D are related?  \n􀀏 A : B :: C : ? -What is the result of applying the transformation A : B to C?  \n1 See [2] for a deeper philosophical discussion of analogical reasoning.  \nThe first two questions can be viewed as discriminative tasks, and could be formulated as classification problems. The third question requires generating an appropriate image to make a valid analogy. Since a model with this capability would be of practical interest, we focus on this question.  \nOur proposed approach is to learn a deep encoder function f : RD ! RK that maps images to an embedding space suitable for reasoning about analogies, and a deep decoder function g : RK ! RD that maps from the embedding back to the image space. (See Figure 1.) Our encoder function is inspired by word2vec [21], GloVe [22] and other embedding methods that map inputs to a space supporting analogies by vector addition. In those models, analogies could be performed via  \nd = arg max","cbCaidmgTW5mq3Ad","https://ap.wps.com/l/cbCaidmgTW5mq3Ad","pdf",3158680,"English","# Abstract\n# Introduction\n# Related Work","[{\"question\":\"What is visual analogy making in this paper?\",\"answer\":\"It transforms a query image using an example pair of related images, producing a completed analogy image.\"},{\"question\":\"How does the model perform analogical reasoning?\",\"answer\":\"It maps images into an embedding space where analogies are carried out with operations such as vector subtraction and addition, then applies a decoder to generate the transformed image.\"},{\"question\":\"What datasets and tasks are used to evaluate the approach?\",\"answer\":\"The paper evaluates visual analogy completion on 2D shapes, demonstrates animation transfer and analogy traversal on animated game sprites, and applies pose/rotation transfer on 3D car models.\"}]","Deep Visual Analogy-Making - Paper | PDF",23]