.png){kind=icon}
返回
DXAI: explaining classification by image decomposition
.png){kind=icon}
OA
AI
DOI：10.1007/s00371-025-04218-8.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We propose a new way to explain and to visualize neural network classification through a decomposition-based explainable AI (DXAI). Instead of providing an explanation heatmap, our method yields a decomposition of the image into class-agnostic and class-distinct parts, with respect to the data and chosen classifier. Following a fundamental signal processing paradigm of analysis and synthesis, the original image is the sum of the decomposed parts. We thus obtain a radically different way of explaining classification. The class-agnostic part ideally is composed of all image features which do not possess class information, where the class-distinct part is its complementary. This new visualization can be more helpful and informative in certain scenarios, especially when the attributes are dense, global, and additive in nature, for instance, when colors or textures are essential for class distinction. Code is available at https://github.com/dxai2024/dxai .
Keyword:
Image classification
Explainable AI
Image decomposition
Style transfer
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
T
IF:
0
论文数:
369
被引数:
0
机构
引用论文
"Why Should I Trust You?"“我为什么要相信你？”.png)
Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIF0
PREAI
分享收藏Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism使用注意力机制学习视觉解释以用于基于DCNN的图像分类器
PREAI
分享收藏Explainable Image Classification: The Journey So Far and the Road Ahead可解释的图像分类: 迄今为止的旅程和未来的道路AI
OAAI
AIIF5
OAAI分享收藏Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationGrad-cam: 通过基于梯度的定位从深度网络进行视觉解释OAAI
OAAI分享收藏
查看更多内容