将图像可视化方法适配到时序异常检测模型，提升可解释性。
From CNN to CNN + RNN: Adapting Visualization Techniques for Time-Series Anomaly Detection
- 用VGG19+GRU处理视频序列，结合梯度可视化技术
- 成功将Saliency与Grad-CAM用于时序模型，揭示关键帧特征
- 适合需要模型透明性的安全、医疗等高风险场景
深度神经网络在解决复杂问题上表现优异，但常被视为“黑箱”，限制了其在需透明性和可解释性的领域（如安全）的应用。欧盟《通用数据保护条例》（GDPR）强调决策可解释的重要性。本文研究基于卷积循环神经网络（CNN + RNN）与TimeDistributed层的异常检测模型的可视化方法。模型采用VGG19进行卷积特征提取，搭配GRU对实时视频数据进行序列分析。由于序列元素独立处理，导致梯度传播困难，时间信息被割裂。本文将Saliency图和Grad-CAM等静态图像可视化技术适配至该架构，克服了时序建模中的可解释性挑战，为缺乏专用方法时提供过渡性解决方案。
原文摘要 · Abstract (English)
Deep neural networks are highly effective in solving complex problems but are often viewed as "black boxes," limiting their adoption in contexts where transparency and explainability are essential. This lack of visibility raises ethical and legal concerns, particularly in critical areas like security, where automated decisions can have significant consequences. The General Data Protection Regulation (GDPR) underscores the importance of justifying these decisions. In this work, we explore visualization techniques to improve the understanding of anomaly detection models based on convolutional recurrent neural networks (CNN + RNN) with a TimeDistributed layer. Our model combines VGG19 for convolutional feature extraction and a GRU layer for sequential analysis of real-time video data. While suitable for temporal data, this structure complicates gradient propagation, as sequence elements are processed independently, dissociating temporal information. We adapt visualization techniques such as saliency maps and Grad-CAM to address these challenges. This article highlights the difficulties in visually interpreting video-based models and demonstrates how techniques for static images can be adapted to recurrent architectures, offering a transitional solution in the absence of dedicated methods.
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。