通過任務向量定制擴展個性化美學評估

Scaling Up Personalized Aesthetic Assessment via Task Vector Customization

July 9, 2024

作者: Jooyeol Yun, Jaegul Choo

cs.AI

摘要

個性化圖像美學評估任務旨在根據少量用戶提供的輸入，定制美學分數預測模型以符合個人偏好。然而，目前方法的可擴展性和泛化能力受到其依賴昂貴的精心編輯數據庫的限制。為了克服這個長期存在的擴展性挑戰，我們提出了一種獨特的方法，利用現成的數據庫進行一般圖像美學評估和圖像質量評估。具體來說，我們將每個數據庫視為一個獨特的圖像分數回歸任務，展示了不同程度的個性化潛力。通過確定代表每個數據庫特定特徵的任勞任怨向量的最佳組合，我們成功地為個人創建了個性化模型。這種整合多個模型的方法使我們能夠利用大量數據。我們的大量實驗證明了我們的方法在泛化到以前未見領域方面的有效性，這是以前方法難以實現的挑戰，使其在實際情況下非常適用。我們的新方法通過為個性化美學評估提供可擴展解決方案並為未來研究建立高標準，顯著推動了該領域的發展。

English

The task of personalized image aesthetic assessment seeks to tailor aesthetic score prediction models to match individual preferences with just a few user-provided inputs. However, the scalability and generalization capabilities of current approaches are considerably restricted by their reliance on an expensive curated database. To overcome this long-standing scalability challenge, we present a unique approach that leverages readily available databases for general image aesthetic assessment and image quality assessment. Specifically, we view each database as a distinct image score regression task that exhibits varying degrees of personalization potential. By determining optimal combinations of task vectors, known to represent specific traits of each database, we successfully create personalized models for individuals. This approach of integrating multiple models allows us to harness a substantial amount of data. Our extensive experiments demonstrate the effectiveness of our approach in generalizing to previously unseen domains-a challenge previous approaches have struggled to achieve-making it highly applicable to real-world scenarios. Our novel approach significantly advances the field by offering scalable solutions for personalized aesthetic assessment and establishing high standards for future research. https://yeolj00.github.io/personal-projects/personalized-aesthetics/