arXiv cs.AI· Xu Zhang, Haohan Wang, Zheng Zhang, Yingjie Xia, Wei Feng, Honghe Zhu, Jingjing Lv, Changping Peng, Xuheng Qin, Zehua Zhang, Zheng Luo, Qicheng Li·· 6 天前AI 评分22
ECC：基于点击率驱动与属性解耦的广告图像编辑方法
Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment
AI 导读
针对电商广告创意优化，研究者提出 ECC 方法，将创意优化重构为细粒度编辑而非从零生成，选择性优化损害 CTR 的属性并保留有益属性。ECC 通过 ANOVA 和随机森林回归识别出 28 个与 CTR 显著相关的属性，并引入一致偏好优化（CPO）策略，通过对语义等价的乱序建议施加一致性约束来缓解 DPO 过拟合。
正文 · 原文
Authors:Xu Zhang, Haohan Wang, Zheng Zhang, Yingjie Xia, Wei Feng, Honghe Zhu, Jingjing Lv, Changping Peng, Xuheng Qin, Zehua Zhang, Zheng Luo, Qicheng Li
Abstract:The optimization objective for e-commerce advertising creatives has shifted from aesthetic quality to online business metrics like click-through rate (CTR). Recent methods generate appealing ad images from product images by constructing CTR-based reward signals and refining prompt generation via Reinforcement Learning. Such paradigms equally penalize all attributes within an underperforming image, even though some are actually beneficial to clicks. In this work, we propose Evolving Creatives with Clicks (ECC), which reformulates creative optimization as fine-grained editing rather than generation from scratch. ECC selectively refines attributes that hurt CTR while preserving those that contribute positively. Specifically, faced with a rich attribute space across massive images, ECC first identifies 28 attributes significantly correlated with CTR via ANOVA and Random Forest regression. Based on attribute contrasts between images with disparate CTRs, we instruction-tune a prompt model to generate editing suggestions, then refine it with real click preferences since reference-derived suggestions are not uniformly beneficial. Furthermore, we introduce Consistent Preference Optimization (CPO) as ECC's preference optimization strategy, which enforces consistency across semantically equivalent shuffled suggestions to mitigate DPO overfitting and improve preference generalization. Extensive experiments demonstrate that ECC significantly improves the CTR of ad images, outperforming state-of-the-art models by a substantial margin. The complete data pipeline, including attribute extraction and analysis, the resulting dataset, and source code will be released upon acceptance.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.13066 [cs.CV] |
| (or arXiv:2610.13066v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13066 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xu Zhang [view email]
[v1]
Fri, 9 Oct 2026 06:26:24 UTC (8,651 KB)
来源：arXiv cs.AI · arxiv.org