论文标题
评估有关时间色恒定的深度学习模型的基于显着性的解释的忠诚
Evaluating the Faithfulness of Saliency-based Explanations for Deep Learning Models for Temporal Colour Constancy
论文作者
论文摘要
深度学习模型的不透明度限制了他们的调试和改进。据称，通过基于显着的策略（例如注意）增强深层模型，以帮助更好地了解黑盒模型的决策过程。但是，最近的一些作品挑战了显着性在自然语言处理领域（NLP）领域的忠诚，质疑注意力重量对模型的真正决策过程的遵守。我们通过评估第一次应用于视频处理任务的模型内显着性的忠诚，即时间颜色恒定。我们通过适应目标任务的两个测试来进行评估，这是NLP文献的忠诚测试，我们的方法论是我们的贡献的一部分。我们表明，注意力无法实现忠诚，而信心（一种特定类型的模型内视觉显着性）成功。
The opacity of deep learning models constrains their debugging and improvement. Augmenting deep models with saliency-based strategies, such as attention, has been claimed to help get a better understanding of the decision-making process of black-box models. However, some recent works challenged saliency's faithfulness in the field of Natural Language Processing (NLP), questioning attention weights' adherence to the true decision-making process of the model. We add to this discussion by evaluating the faithfulness of in-model saliency applied to a video processing task for the first time, namely, temporal colour constancy. We perform the evaluation by adapting to our target task two tests for faithfulness from recent NLP literature, whose methodology we refine as part of our contributions. We show that attention fails to achieve faithfulness, while confidence, a particular type of in-model visual saliency, succeeds.
