.png){kind=icon}
返回
Explaining Cross-domain Recognition with Interpretable Deep Classifier
.png){kind=icon}
OA
AI
DOI：10.1145/3623399.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The recent advances in deep learning predominantly construct models in their internal representations, and it is opaque to explain the rationale behind and decisions to human users. Such explainability is especially essential for domain adaptation, whose challenges require developing more adaptive models across different domains. In this article, we ask the question: How much does each sample in the source domain contribute to the network's prediction on the samples from the target domain? To address this, we devise a novel Interpretable Deep Classifier (IDC) that learns the nearest source samples of a target sample as evidence upon which the classifier makes the decision. Technically, IDC maintains a differentiable memory bank for each category, and the memory slot derives a form of key-value pair. The key records the features of discriminative source samples, and the value stores the corresponding properties, e.g., representative scores of the features for describing the category. IDC computes the loss between the output of IDC and the labels of source samples to back-propagate to adjust the representative scores and update the memory banks. Extensive experiments on Office-Home and VisDA-2017 datasets demonstrate that our IDC leads to a more explainable model with almost no accuracy degradation and effectively calibrates classification for optimum reject options. More remarkably, when taking IDC as a prior interpreter, capitalizing on 0.1% source training data selected by IDC still yields superior results than that uses full training set on VisDA-2017 for unsupervised domain adaptation.
Keyword:
Explainable
unsupervised domain adaptation
memory matching
期刊
IF:
6
论文数:
2.0K
被引数:
5.4K
机构
暂无机构信息
引用论文
Dimensioning Methodology of an Energy Storage System Based on Supercapacitors for Grid Code Compliance of a Wave Power Plant.png)
EnergiesOAAI
EnergiesIF0
OAAI分享收藏Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI可解释人工智能 (XAI): 负责任人工智能的概念、分类、机遇和挑战INFORMATION FUSION
OAAI
INFORMATION FUSIONIF15.5
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分享收藏分享收藏 没有更多内容
没有更多内容