{"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/ls-gan-iterative-language-based-image","title":"LS-GAN: Iterative Language-based Image Manipulation via Long and Short Term Consistency Reasoning","arxiv_id":null,"date":"2022-10-22","proceeding":"journal 2022 10","authors":["Gaoxiang Cong","Liang Li","Zhenhuan Liu","Yunbin Tu","Weijun Qin","Shenyuan Zhang","Chengang Yan","Wenyu Wang","Bin Jiang"],"abstract":"Iterative language-based image manipulation aims to edit images step by step according to user's linguistic instructions. The existing methods mostly focus on aligning the attributes and appearance of new-added visual elements with current instruction. However, they fail to maintain consistency between instructions and images as iterative rounds increase. To address this issue, we propose a novel Long and Short term consistency reasoning Generative Adversarial Network (LS-GAN), which enhances the awareness of previous objects with current instruction and better maintains the consistency with the user's intent under the continuous iterations. Specifically, we first design a Context-aware Phrase Encoder (CPE) to learn the user's intention by extracting different phrase-level information about the instruction. Further, we introduce a Long and Short term Consistency Reasoning (LSCR) mechanism. The long-term reasoning improves the model on semantic understanding and positional reasoning, while short-term reasoning ensures the ability to construct visual scenes based on linguistic instructions. Extensive results show that LS-GAN improves the generation quality in terms of both object identity and position, and achieves the state-of-the-art performance on two public datasets.","url_abs":"https://dl.acm.org/doi/abs/10.1145/3503161.3548206","url_pdf":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548206","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":"ls-gan-iterative-language-based-image","repo_url":"https://github.com/galaxycong/ls-gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"ls-gan-iterative-language-based-image","repo_url":"https://github.com/2023-MindSpore-4/Code12/tree/main/liliang/LSCR_mds-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-manipulation","task_name":"Image Manipulation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}