论文标题
视觉分析和转向零射击学习
Visually Analyzing and Steering Zero Shot Learning
论文作者
论文摘要
我们提出了一个视觉分析系统，以帮助用户分析和引导零击学习模型。零击学习已成为一种可行的方案，用于对不包含标记示例的数据进行分类，因此是一种有希望的方法，可以最大程度地减少人类的数据注释。但是，了解零射击学习失败的位置，这种失败的原因以及用户如何修改模型以防止此类失败是一项挑战。我们的可视化系统旨在帮助用户诊断和理解此类模型中的错误预测，以便在应用于与培训过程中未看到的类别相关的数据时，他们可以深入了解模型的行为。通过使用情况，我们强调了我们的系统如何帮助用户提高零局学习的性能。
We propose a visual analytics system to help a user analyze and steer zero-shot learning models. Zero-shot learning has emerged as a viable scenario for categorizing data that consists of no labeled examples, and thus a promising approach to minimize data annotation from humans. However, it is challenging to understand where zero-shot learning fails, the cause of such failures, and how a user can modify the model to prevent such failures. Our visualization system is designed to help users diagnose and understand mispredictions in such models, so that they may gain insight on the behavior of a model when applied to data associated with categories not seen during training. Through usage scenarios, we highlight how our system can help a user improve performance in zero-shot learning.
