检查带有额外统计信息的Transformer模型的可解释性
Inspecting Explainability of Transformer Models with Additional Statistical Information
AI总结：
针对Transformer可视化解释的局限，提出利用层归一化层令牌统计信息的方法，有效解释Swin Transformer和ViT的可解释性。
摘要：
近年来，Transformer在视觉领域变得越来越流行，因此需要找到一种有效的方法通过可视化来解释Transformer模型。在最近的工作中，Chefer等人通过结合注意力层来展示每个图像块的重要性，能够有效地在视觉和多模态任务上可视化Transformer。然而，当应用于Transformer的其他变体（如Swin Transformer）时，该方法无法聚焦于预测对象。我们的方法通过考虑层归一化层中令牌的统计信息，展示了在解释Swin Transformer和ViT的可解释性方面的强大能力。
英文摘要：
Transformer becomes more popular in the vision domain in recent years so there is a need for finding an effective way to interpret the Transformer model by visualizing it. In recent work, Chefer et al. can visualize the Transformer on vision and multi-modal tasks effectively by combining attention layers to show the importance of each image patch. However, when applying to other variants of Transformer such as the Swin Transformer, this method can not focus on the predicted object. Our method, by considering the statistics of tokens in layer normalization layers, shows a great ability to interpret the explainability of Swin Transformer and ViT.
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。
