可视化Transformer看图过程，帮人理解模型决策逻辑。
ViT-Explainer: An Interactive Walkthrough of the Vision Transformer Pipeline
- 用动画展示图像转片段、注意力计算到分类的完整流程。
- 支持点击查看每一步的注意力分布，定位关键视觉区域。
- 适合想搞懂ViT原理的学生或研究人员使用。
基于Transformer的架构已成为自然语言处理和计算机视觉的通用骨干。然而，理解这些模型的运行机制仍具挑战性，尤其是在视觉任务中，图像被处理为片段标记序列。现有可解释性工具通常只关注孤立组件或面向专家分析，缺乏对完整推理流程的引导式端到端理解。为此，我们提出ViT-Explainer，一个基于网页的交互式系统，集成可视化展示视觉Transformer的推理全过程，从片段标记化到最终分类。系统结合动态演示、片段级注意力叠加以及适配视觉的Logit Lens，支持引导式与自由探索两种模式。六名参与者用户研究显示，ViT-Explainer易于学习和使用，有助于用户理解和解释视觉Transformer的行为。
原文摘要 · Abstract (English)
Transformer-based architectures have become the shared backbone of natural language processing and computer vision. However, understanding how these models operate remains challenging, particularly in vision settings, where images are processed as sequences of patch tokens. Existing interpretability tools often focus on isolated components or expert-oriented analysis, leaving a gap in guided, end-to-end understanding of the full inference pipeline. To bridge this gap, we present ViT-Explainer, a web-based interactive system that provides an integrated visualization of Vision Transformer inference, from patch tokenization to final classification. The system combines animated walkthroughs, patch-level attention overlays, and a vision-adapted Logit Lens within both guided and free exploration modes. A user study with six participants suggests that ViT-Explainer is easy to learn and use, helping users interpret and understand Vision Transformer behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。