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 discuss connections of our approach to diversity, equity, and inclusion in generative machine learning more generally, and computational creativity specifically. An implementation of our algorithm is available at https://github.com/sebastianberns/diversity-weights

翻译：大型数据驱动图像模型被广泛用于支持创意与艺术创作。在当前主流的分布拟合范式下，数据集被视为需要尽可能精确逼近的"真实标准"。然而，许多创意应用要求输出具备高度多样性，创作者往往致力于主动偏离给定数据分布。我们认为，为适应更高输出多样性的需求，有必要将建模目标从纯粹的模式覆盖调整为模式平衡。本文提出多样性权重训练方案，通过平衡训练数据集中的模态分布来提升模型的输出多样性。在受控环境中的初步实验验证了本方法的潜力，我们进一步讨论了该方法与生成式机器学习中更广义的多样性、公平性、包容性议题，特别是与计算创造力的关联。算法实现代码见 https://github.com/sebastianberns/diversity-weights