Image Style Transfer Model Retrieval using Transformer Encoder and Learning to Rank

• Item type: Trans(1)
• 公開日: 2026-01-26
• タイトル / 言語: ja
• タイトル: Image Style Transfer Model Retrieval using Transformer Encoder and Learning to Rank
• タイトル / 言語: en
• タイトル: Image Style Transfer Model Retrieval using Transformer Encoder and Learning to Rank
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [研究論文] machine learning model retrieval, learning to rank, image generation
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: University of Hyogo
• 著者所属: Shizuoka University
• 著者所属: LY Corporation
• 著者所属: University of Hyogo
• 著者所属(英): en
• 著者所属(英): University of Hyogo
• 著者所属(英): en
• 著者所属(英): Shizuoka University
• 著者所属(英): en
• 著者所属(英): LY Corporation
• 著者所属(英): en
• 著者所属(英): University of Hyogo
• 著者名: Huu-Long,Pham; Yoshiyuki,Shoji; Sumio,Fujita; Hiroaki,Ohshima
• 著者名(英): Huu-Long Pham; Yoshiyuki Shoji; Sumio Fujita; Hiroaki Ohshima
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Image style transfer, a prominent application of generative AI, has significantly impacted digital content creation. However, the proliferation of style transfer models makes it challenging for users to search and find a model that generates a desired style. Usually, searching for an appropriate model is a manually intensive and computationally prohibitive task. To address this, we propose an effective method for style transfer model retrieval. Our method takes an image exhibiting a target style as a query and ranks a collection of available models based on their ability to reproduce that style. Our approach uses a Vision Transformer to encode the query image's features into patch-level embeddings. Concurrently, style transfer models are represented as learnable embedding vectors. A transformer encoder then fuses query image and model embeddings to compute a relevance score, indicating the model's suitability for generating style similar to the query image's. Our method is optimized end-to-end using a hybrid loss function that combines Binary Cross Entropy (BCE) with a Learning-to-Rank objective. To evaluate the proposed method, we constructed a benchmark dataset of 10,000 images, generated from 100 unique style transfer models applied to 100 distinct content images. Our experiments demonstrate the effectiveness of the proposed method's retrieval performance as well as its efficiency.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.34(2026) (online); ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Image style transfer, a prominent application of generative AI, has significantly impacted digital content creation. However, the proliferation of style transfer models makes it challenging for users to search and find a model that generates a desired style. Usually, searching for an appropriate model is a manually intensive and computationally prohibitive task. To address this, we propose an effective method for style transfer model retrieval. Our method takes an image exhibiting a target style as a query and ranks a collection of available models based on their ability to reproduce that style. Our approach uses a Vision Transformer to encode the query image's features into patch-level embeddings. Concurrently, style transfer models are represented as learnable embedding vectors. A transformer encoder then fuses query image and model embeddings to compute a relevance score, indicating the model's suitability for generating style similar to the query image's. Our method is optimized end-to-end using a hybrid loss function that combines Binary Cross Entropy (BCE) with a Learning-to-Rank objective. To evaluate the proposed method, we constructed a benchmark dataset of 10,000 images, generated from 100 unique style transfer models applied to 100 distinct content images. Our experiments demonstrate the effectiveness of the proposed method's retrieval performance as well as its efficiency.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.34(2026) (online); ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11464847
• 書誌情報: 情報処理学会論文誌データベース（TOD）; 巻 19, 号 1, 発行日 2026-01-26
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7799
• 出版者 / 言語: ja
• 出版者: 情報処理学会