{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bilinear-representation-for-language-based","title":"Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks","arxiv_id":"1903.07499","date":"2019-03-18","proceeding":null,"authors":["Xiaofeng Mao","Yuefeng Chen","Yuhong Li","Tao Xiong","Yuan He","Hui Xue"],"abstract":"The task of Language-Based Image Editing (LBIE) aims at generating a target\nimage by editing the source image based on the given language description. The\nmain challenge of LBIE is to disentangle the semantics in image and text and\nthen combine them to generate realistic images. Therefore, the editing\nperformance is heavily dependent on the learned representation. In this work,\nconditional generative adversarial network (cGAN) is utilized for LBIE. We find\nthat existing conditioning methods in cGAN lack of representation power as they\ncannot learn the second-order correlation between two conditioning vectors. To\nsolve this problem, we propose an improved conditional layer named Bilinear\nResidual Layer (BRL) to learning more powerful representations for LBIE task.\nQualitative and quantitative comparisons demonstrate that our method can\ngenerate images with higher quality when compared to previous LBIE techniques.","url_abs":"http://arxiv.org/abs/1903.07499v1","url_pdf":"http://arxiv.org/pdf/1903.07499v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bilinear-representation-for-language-based","repo_url":"https://github.com/vtddggg/BilinearGAN_for_LBIE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.07499","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}