ViTmiX：通过混合可视化方法增强的Vision Transformer可解释性
ViTmiX: Vision Transformer Explainability Augmented by Mixed Visualization Methods
AI总结：
本研究提出ViTmiX混合方法，结合多种可解释性技术以克服单一方法的局限，显著提升Vision Transformer模型的可解释性，并引入基于抽屉原理的事后度量法及几何平均修改，在目标分割任务中表现优异。
摘要：
Vision Transformers (ViT) 的最新进展在各种视觉识别任务中展现了卓越的结果，这得益于它们通过自注意力机制捕获图像中长距离依赖关系的能力。然而，ViT模型的复杂性质需要稳健的可解释性方法来揭示其决策过程。可解释人工智能 (XAI) 通过提供对模型预测的洞察，在提高模型透明度和可信度方面发挥着至关重要的作用。当前基于分层相关性传播 (LRP) 和基于梯度的方法等可视化技术的ViT可解释性方法，已显示出有希望但有时有限的结果。在本研究中，我们探索了一种混合方法，将多种可解释性技术混合以克服这些限制并增强ViT模型的可解释性。我们的实验表明，与单独的方法相比，这种混合方法显著提高了ViT模型的可解释性。我们还对现有技术进行了修改，例如使用几何平均进行混合，这在目标分割任务中展示了显著的结果。为了量化可解释性的增益，我们通过应用抽屉原理引入了一种新颖的事后可解释性度量方法。这些发现强调了为ViT模型改进和优化可解释性方法的重要性，为基于XAI的可靠分割铺平了道路。
英文摘要：
Recent advancements in Vision Transformers (ViT) have demonstrated exceptional results in various visual recognition tasks, owing to their ability to capture long-range dependencies in images through self-attention mechanisms. However, the complex nature of ViT models requires robust explainability methods to unveil their decision-making processes. Explainable Artificial Intelligence (XAI) plays a crucial role in improving model transparency and trustworthiness by providing insights into model predictions. Current approaches to ViT explainability, based on visualization techniques such as Layer-wise Relevance Propagation (LRP) and gradient-based methods, have shown promising but sometimes limited results. In this study, we explore a hybrid approach that mixes multiple explainability techniques to overcome these limitations and enhance the interpretability of ViT models. Our experiments reveal that this hybrid approach significantly improves the interpretability of ViT models compared to individual methods. We also introduce modifications to existing techniques, such as using geometric mean for mixing, which demonstrates notable results in object segmentation tasks. To quantify the explainability gain, we introduced a novel post-hoc explainability measure by applying the Pigeonhole principle. These findings underscore the importance of refining and optimizing explainability methods for ViT models, paving the way to reliable XAI-based segmentations.
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。
