arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.14892cs.LG
收藏

潜在污染模型:3D图像合成中隐藏的碳足迹

Latent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis

Heidelberg University Hospital(海德堡大学医院);German Centre for Cardiovascular Research (DZHK)(德国心血管研究中心);AI Health Innovation Cluster (AIH)(AI健康创新集群)

Marvin Seyfarth, Salman Ul Hassan Dar, Sandy Engelhardt

AI总结:

本研究分析2D和3D潜在扩散模型的碳排放,发现大尺寸图像合成排放最显著,训练排放相当于驾车10-90公里,数据生成高达3345公里,强调需制定可持续策略。

摘要:

当代生成式人工智能的发展正在迅速改变医学人工智能领域。这些发展主要由大型数据集的可用性和高计算能力所驱动,这促进了模型容量的显著增加。尽管这些模型具有相当大的潜力,但它们需要极高的电力,导致高二氧化碳(CO2)排放。鉴于这类模型对环境造成的危害,目前对这些模型的碳足迹关注甚少。本研究分析了2D和3D潜在扩散模型(LDMs)在训练和数据生成阶段的碳排放,揭示了一个令人惊讶的发现:大尺寸图像的合成对这些排放的贡献最为显著。我们评估了不同场景,包括模型大小、图像尺寸、分布式训练和数据生成步骤。我们的研究结果揭示了这些模型产生的大量碳排放,其中训练2D和3D模型的排放量分别相当于驾驶汽车行驶10公里和90公里。数据生成过程更为显著,2D模型的CO2排放量相当于驾驶160公里,而3D合成则相当于驾驶高达3345公里。此外,我们发现实验地点可使碳排放增加多达94倍,甚至一年中的时间也能影响排放多达50%。这些数字令人震惊,考虑到它们仅代表每个模型的一次训练和数据生成阶段。我们的结果强调了在生成式人工智能中制定环境可持续策略的迫切需求。

英文摘要:

Contemporary developments in generative AI are rapidly transforming the field of medical AI. These developments have been predominantly driven by the availability of large datasets and high computing power, which have facilitated a significant increase in model capacity. Despite their considerable potential, these models demand substantially high power, leading to high carbon dioxide (CO2) emissions. Given the harm such models are causing to the environment, there has been little focus on the carbon footprints of such models. This study analyzes carbon emissions from 2D and 3D latent diffusion models (LDMs) during training and data generation phases, revealing a surprising finding: the synthesis of large images contributes most significantly to these emissions. We assess different scenarios including model sizes, image dimensions, distributed training, and data generation steps. Our findings reveal substantial carbon emissions from these models, with training 2D and 3D models comparable to driving a car for 10 km and 90 km, respectively. The process of data generation is even more significant, with CO2 emissions equivalent to driving 160 km for 2D models and driving for up to 3345 km for 3D synthesis. Additionally, we found that the location of the experiment can increase carbon emissions by up to 94 times, and even the time of year can influence emissions by up to 50%. These figures are alarming, considering they represent only a single training and data generation phase for each model. Our results emphasize the urgent need for developing environmentally sustainable strategies in generative AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑