发表机构
Instituto Politécnico Nacional（墨西哥国家理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对AI生成艺术可能抄袭原作的问题，采用带冻结CLIP编码器的孪生网络，构建配对图像数据集，实现99.4%测试准确率，证明语义-视觉嵌入的有效性。
AI 中文摘要
AI生成艺术引发了关于潜在抄袭的争论，因为这些图像可能与现有艺术作品极为相似。本研究量化了原作与AI生成对应图像之间的相似性，特别是由Stable Diffusion XL Refiner 1.0生成的图像。我们使用带有冻结CLIP编码器的孪生网络（Siamese Networks）和通过三元组损失优化的余弦相似度。通过图像到图像生成和自定义提示构建了由原作与生成图像配对组成的数据集，该数据集补充了语义描述符和BLIP-2标题。先前研究报告称风格复制率高达81%，视觉相似度达90%。我们的结果显示出高判别性能：训练准确率达到99.9%，最佳模型配置实现了99.4%的测试准确率，且类间分离度强（δμ=0.677），证明了我们的语义-视觉嵌入的有效性。
英文摘要
AI-generated art has sparked debates around potential plagiarism, as these images may closely resemble existing artworks. This research quantifies the similarity between original pieces and AI-generated counterparts, particularly those produced by the Stable Diffusion XL Refiner 1.0. We use Siamese Networks with frozen CLIP encoders and cosine similarity optimized through triplet loss. A dataset of paired original and generated images was built using image-to-image generation and custom prompts, enriched with semantic descriptors and BLIP-2 captions. Prior studies report up to 81\% style replication and 90\% visual similarity. Our results show high discriminative performance: training accuracy reached 99.9\%, and the best model configuration achieved 99.4\% test accuracy with strong inter-class separation ($δμ$ = 0.677), demonstrating the effectiveness of our semantic-visual embeddings.
CommentsAccepted to LatinX in AI Research Workshop at Neurips 2025
