通过可视化激活通道分析模型如何区分类别，帮助理解深度网络决策过程。
ChannelExplorer: Exploring Class Separability Through Activation Channel Visualization
- 用三视图可视化各层激活，揭示类别间与类内混淆情况。
- 量化激活重叠度并识别关键贡献通道，提升可解释性。
- 适用于CNN、GAN、Stable Diffusion等模型，适合研究人员和工程师使用。
深度神经网络在众多视觉任务中表现卓越，但其内部行为仍难以理解，尤其是各层与激活通道如何影响类别可分性。我们提出ChannelExplorer，一个交互式可视化分析工具，用于分析基于图像的模型输出，侧重数据驱动洞察而非架构分析。该工具通过三个协同视图呈现激活：散点图视图揭示类间与类内混淆，杰卡德相似性视图量化激活重叠，热力图视图检查激活通道模式。方法支持多种模型架构，包括CNN、GAN、ResNet及Stable Diffusion。通过四个应用场景验证：(1) 生成ImageNet的类别层次结构，(2) 发现误标注图像，(3) 识别激活通道贡献，(4) 定位Stable Diffusion中的潜在状态位置。最后通过专家用户评估工具有效性。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) achieve state-of-the-art performance in many vision tasks, yet understanding their internal behavior remains challenging, particularly how different layers and activation channels contribute to class separability. We introduce ChannelExplorer, an interactive visual analytics tool for analyzing image-based outputs across model layers, emphasizing data-driven insights over architecture analysis for exploring class separability. ChannelExplorer summarizes activations across layers and visualizes them using three primary coordinated views: a Scatterplot View to reveal inter- and intra-class confusion, a Jaccard Similarity View to quantify activation overlap, and a Heatmap View to inspect activation channel patterns. Our technique supports diverse model architectures, including CNNs, GANs, ResNet and Stable Diffusion models. We demonstrate the capabilities of ChannelExplorer through four use-case scenarios: (1) generating class hierarchy in ImageNet, (2) finding mislabeled images, (3) identifying activation channel contributions, and(4) locating latent states' position in Stable Diffusion model. Finally, we evaluate the tool with expert users.
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。