用深度模型量化AI画作与原作的相似度，揭示其潜在抄袭风险。
Measuring Similarity between Artistic and AI Generated Images using Siamese Neural Networks
- 构建配对数据集，结合语义描述与图像特征，用孪生网络比对原作与AI生成图。
- 模型测试准确率达99.4%，类间分离度0.677，证明能有效区分真实与生成作品。
- 适合关注AI艺术版权、内容检测或生成模型评估的研究者阅读。
AI生成艺术引发了关于潜在剽窃的争议，因其图像可能高度模仿现有作品。本研究量化了原创作品与AI生成图像之间的相似性，特别针对Stable Diffusion XL Refiner 1.0生成的内容。采用冻结的CLIP编码器和余弦相似度，通过三元组损失优化的孪生神经网络。构建了一个包含配对原作与生成图像的数据集，结合图像到图像生成、自定义提示词，并加入语义描述与BLIP-2生成的标题。先前研究报道风格复制率高达81%，视觉相似度达90%。本研究结果表明模型具备高判别能力：训练准确率达到99.9%，最佳模型配置在测试中达到99.4%准确率，类间分离度Δμ = 0.677，充分验证了所提语义-视觉嵌入的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。