首次系统分析图像生成中多维度的权衡关系，揭示模型优劣背后的深层机制。
Trade-offs in Image Generation: How Do Different Dimensions Interact?
- 构建跨10维度、4万样本的TRIG-Bench数据集，支持细粒度评估
- 提出TRIGScore自动评分工具，可适配不同生成维度的评测需求
- 开发关系识别系统生成维度权衡图（DTM），助力模型优化
文本到图像（T2I）与图像到图像（I2I）生成模型性能常受质量、对齐、多样性、鲁棒性等多维度影响。然而由于缺乏能精细量化这些权衡的数据集及单一指标难以覆盖多维度，此类研究长期受限。为此，本文提出TRIG-Bench，涵盖10个维度（真实感、原创性、美学、内容、关系、风格、知识、模糊性、毒性、偏见）、共40,200个样本，并覆盖132种维度组合。我们进一步开发了基于视觉语言模型的TRIGScore评分器，可自适应不同维度评估。基于此，我们在T2I和I2I任务上评估了14个模型。此外，提出关系识别系统以生成维度权衡图（DTM），可视化模型在各维度间的权衡特性。实验表明，DTM能持续提供对模型能力权衡的全面理解；尤其发现，通过在DTM指导下微调，可有效缓解模型特定维度的缺陷，提升整体表现。代码已开源。
原文摘要 · Abstract (English)
Model performance in text-to-image (T2I) and image-to-image (I2I) generation often depends on multiple aspects, including quality, alignment, diversity, and robustness. However, models' complex trade-offs among these dimensions have rarely been explored due to (1) the lack of datasets that allow fine-grained quantification of these trade-offs, and (2) the use of a single metric for multiple dimensions. To bridge this gap, we introduce TRIG-Bench (Trade-offs in Image Generation), which spans 10 dimensions (Realism, Originality, Aesthetics, Content, Relation, Style, Knowledge, Ambiguity, Toxicity, and Bias), contains 40,200 samples, and covers 132 pairwise dimensional subsets. Furthermore, we develop TRIGScore, a VLM-as-judge metric that automatically adapts to various dimensions. Based on TRIG-Bench and TRIGScore, we evaluate 14 models across T2I and I2I tasks. In addition, we propose the Relation Recognition System to generate the Dimension Trade-off Map (DTM) that visualizes the trade-offs among model-specific capabilities. Our experiments demonstrate that DTM consistently provides a comprehensive understanding of the trade-offs between dimensions for each type of generative model. Notably, we show that the model's dimension-specific weaknesses can be mitigated through fine-tuning on DTM to enhance overall performance. Code is available at: https://github.com/fesvhtr/TRIG
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。