arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.09685cs.CV
收藏

接地视觉示意图

Grounding Visual Explanations

UC Berkeley(加州大学伯克利分校);University of Amsterdam(阿姆斯特丹大学)

Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, Zeynep Akata

摘要:

现有的视觉解释生成代理学习流利地证明类预测。然而,他们可能会提到反映强烈类别先验的视觉属性,尽管证据可能实际上并不存在于图像中。这是特别令人担忧的,因为最终这些代理无法与人类用户建立信任。为了克服这一限制,我们提出了一个短语评论模型来改进生成的候选解释,这些解释用翻转的短语来增强,我们在训练时将其用作负面示例。在推理时,我们的短语评论模型将图像和候选解释作为输入,并输出一个分数,指示候选解释在图像中的基础。我们可解释的人工智能智能体能够为另一种预测提供反论据,即反事实,以及证明正确分类决策的解释。我们的模型通过提及图像中的短语来提高CUB数据集上细粒度分类决策的文本解释质量。此外,在FOIL任务中,我们的智能体检测句子中的错误,为不正确的短语提供理由,并比其他模型更好地纠正它。

英文摘要:

Existing visual explanation generating agents learn to fluently justify a class prediction. However, they may mention visual attributes which reflect a strong class prior, although the evidence may not actually be in the image. This is particularly concerning as ultimately such agents fail in building trust with human users. To overcome this limitation, we propose a phrase-critic model to refine generated candidate explanations augmented with flipped phrases which we use as negative examples while training. At inference time, our phrase-critic model takes an image and a candidate explanation as input and outputs a score indicating how well the candidate explanation is grounded in the image. Our explainable AI agent is capable of providing counter arguments for an alternative prediction, i.e. counterfactuals, along with explanations that justify the correct classification decisions. Our model improves the textual explanation quality of fine-grained classification decisions on the CUB dataset by mentioning phrases that are grounded in the image. Moreover, on the FOIL tasks, our agent detects when there is a mistake in the sentence, grounds the incorrect phrase and corrects it significantly better than other models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑