Large data-driven image models are extensively used to support creative and artistic work. Under the currently predominant distribution-fitting paradigm, a dataset is treated as ground truth to be approximated as closely as possible. Yet, many creative applications demand a diverse range of output, and creators often strive to actively diverge from a given data distribution. We argue that an adjustment of modelling objectives, from pure mode coverage towards mode balancing, is necessary to accommodate the goal of higher output diversity. We present diversity weights, a training scheme that increases a model's output diversity by balancing the modes in the training dataset. First experiments in a controlled setting demonstrate the potential of our method. We conclude by contextualising our contribution to diversity within the wider debate on bias, fairness and representation in generative machine learning.

翻译：大规模数据驱动的图像模型被广泛用于支持创意与艺术工作。在当前主流的数据分布拟合范式下，数据集被视为需要尽可能精确逼近的基准事实。然而，许多创意应用要求输出具有高度多样性，创作者往往致力于主动偏离给定数据分布。我们认为，为满足更高输出多样性的目标，必须将建模目标从纯粹的模式覆盖调整为模式平衡。我们提出"多样性权重"这一训练方案，通过平衡训练数据集中的模式来提升模型输出多样性。在受控环境下的初步实验展示了该方法的潜力。最后，我们将这一关于多样性的贡献置于生成式机器学习中关于偏见、公平性与表征的广泛讨论中加以阐释。