论文标题
内容掩盖损失：在加固学习绘画代理中类似人类的刷子中风计划
Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent
论文作者
论文摘要
大多数强化学习绘画剂的目的是最大程度地减少目标图像和油漆画布之间的损失。人类画家艺术强调了目标形象的重要特征，而不是简单地再现它（Dipaola 2007）。在RL绘画模型中使用对抗性或L2损失，尽管其最终输出通常是精巧的作品，但会产生一种与人类会产生的序列，因为该模型对目标图像中的抽象特征不了解。为了在不使用昂贵的人类数据的情况下增加模型的类似人类计划，我们引入了一种新的损失功能，以供模型的奖励功能：内容掩盖的损失。在机器人绘画的背景下，内容掩盖损失采用对象检测模型来提取特征，这些特征用于将更高的重量分配给人类对识别内容很重要的画布区域。基于332个人类评估人员的结果表明，与现有方法相比，我们内容掩盖模型制作的数字绘画在中风序列中显示了可检测到的主题，而不会损害最终绘画的质量。我们的代码可从https://github.com/pschaldenbrand/contentmaskedloss获得。
The objective of most Reinforcement Learning painting agents is to minimize the loss between a target image and the paint canvas. Human painter artistry emphasizes important features of the target image rather than simply reproducing it (DiPaola 2007). Using adversarial or L2 losses in the RL painting models, although its final output is generally a work of finesse, produces a stroke sequence that is vastly different from that which a human would produce since the model does not have knowledge about the abstract features in the target image. In order to increase the human-like planning of the model without the use of expensive human data, we introduce a new loss function for use with the model's reward function: Content Masked Loss. In the context of robot painting, Content Masked Loss employs an object detection model to extract features which are used to assign higher weight to regions of the canvas that a human would find important for recognizing content. The results, based on 332 human evaluators, show that the digital paintings produced by our Content Masked model show detectable subject matter earlier in the stroke sequence than existing methods without compromising on the quality of the final painting. Our code is available at https://github.com/pschaldenbrand/ContentMaskedLoss.
