MANTA通过优化适配器组合，在硬件限制下实现高性价比的个性化模型生成。
MANTA -- Model Adapter Native generations that's Affordable
- 提出适配器组合新问题，兼顾硬件约束与成本效益。
- 在COCO数据集上任务多样性胜率达94%，质量胜率达80%。
- 适合需要低成本生成多样化内容的合成数据与艺术创作场景。
现有模型生成算法依赖简单且僵化的适配器选择来实现个性化结果。本文将适配器选择问题推广为更通用的模型-适配器组合问题，并考虑实际硬件和成本约束，提出MANTA方法。在COCO 2014验证集上的实验表明，MANTA在图像任务多样性和质量上优于当前最佳系统，仅带来适度的对齐性能下降。其系统在任务多样性上达到94%的胜率，在任务质量上达80%胜率，展现出在合成数据生成和创意艺术领域的强应用潜力。
原文摘要 · Abstract (English)
The presiding model generation algorithms rely on simple, inflexible adapter selection to provide personalized results. We propose the model-adapter composition problem as a generalized problem to past work factoring in practical hardware and affordability constraints, and introduce MANTA as a new approach to the problem. Experiments on COCO 2014 validation show MANTA to be superior in image task diversity and quality at the cost of a modest drop in alignment. Our system achieves a $94\%$ win rate in task diversity and a $80\%$ task quality win rate versus the best known system, and demonstrates strong potential for direct use in synthetic data generation and the creative art domains.
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。