论文标题
解释和改进：图像字幕模型的LRP推论微调
Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models
论文作者
论文摘要
本文通过除了可视化注意力本身的注意力机制分析了图像字幕模型的预测。我们开发了层面相关性传播（LRP）和基于梯度的解释方法的变体，这些方法是针对带有注意机制的图像字幕模型量身定制的。我们将注意力图的解释性系统地比较与LRP，Grad-CAM和Grad-CAM等解释方法提供的解释相比。我们表明，解释方法在预测的标题中为每个单词提供了同时提供像素图像解释（输入图像的支持和对立像素）和语言解释（支持和对立的单词）。我们通过广泛的实验证明了解释方法1）可以揭示该模型与注意力相比做出决策的其他证据； 2）将与对象位置相关联； 3）有助于“调试”该模型，例如通过分析幻觉对象单词的原因。通过观察到的解释属性，我们进一步设计了LRP推动微调策略，该策略降低了图像字幕模型中对象幻觉的问题，同时还保持了句子流利度。我们使用两种广泛使用的注意机制进行实验：根据添加剂注意计算的自适应注意机制和用缩放点产物计算的多头注意机制。
This paper analyzes the predictions of image captioning models with attention mechanisms beyond visualizing the attention itself. We develop variants of layer-wise relevance propagation (LRP) and gradient-based explanation methods, tailored to image captioning models with attention mechanisms. We compare the interpretability of attention heatmaps systematically against the explanations provided by explanation methods such as LRP, Grad-CAM, and Guided Grad-CAM. We show that explanation methods provide simultaneously pixel-wise image explanations (supporting and opposing pixels of the input image) and linguistic explanations (supporting and opposing words of the preceding sequence) for each word in the predicted captions. We demonstrate with extensive experiments that explanation methods 1) can reveal additional evidence used by the model to make decisions compared to attention; 2) correlate to object locations with high precision; 3) are helpful to "debug" the model, e.g. by analyzing the reasons for hallucinated object words. With the observed properties of explanations, we further design an LRP-inference fine-tuning strategy that reduces the issue of object hallucination in image captioning models, and meanwhile, maintains the sentence fluency. We conduct experiments with two widely used attention mechanisms: the adaptive attention mechanism calculated with the additive attention and the multi-head attention mechanism calculated with the scaled dot product.
