.png){kind=icon}
返回
Neural Logic Vision Language Explainer
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2023.3310277.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
If we compare how humans reason and how deep models reason, humans reason in a symbolic manner with a formal language called logic, while most deep models reason in black-box. A natural question to ask is Do the trained deep models reason similar as humans? or Can we explain the reasoning of deep models in the language of logic?. In this work, we present NeurLogX to explain the reasoning process of deep vision language models in the language of logic. Given a trained vision language model, our method starts by generating reasoning facts through augmenting the input data. We then develop a differentiable inductive logic programming framework to learn interpretable logic rules from the facts. We show our results on various popular vision language models. Interestingly, we observe that almost all of the tested models can reason logically.
Keyword:
Explainable artificial intelligence
vision language pretraining
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
Intercellular Adhesion Molecule 1 (ICAM-1) Gene Variant is Associated with Coronary Artery Calcification Independent of Soluble ICAM-1 Levels细胞间粘附分子1 (ICAM-1) 基因变异与冠状动脉钙化相关，与可溶性ICAM-1水平无关
.png){kind=icon}
PREAI
分享收藏分享收藏分享收藏分享收藏Internal control in PCR for Mycobacterium tuberculosis: usefulness and improvement of the diagnosisOAAI
OAAI分享收藏
分享收藏Research on the Efficiency of Wireless Power Transfer System Based on Multi-Auxiliary Transmitting Coils基于多辅助发射线圈的无线电能传输系统效率研究
PREAI
分享收藏
查看更多内容