Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract)
Abstract
Interpreting deep neural networks through examining neurons offers distinct advantages when it comes to exploring the inner workings of Deep Neural Networks. Previous research has indicated that specific neurons within deep vision networks possess semantic meaning and play pivotal roles in model performance. Nonetheless, the current methods for generating neuron semantics heavily rely on human intervention, which hampers their scalability and applicability. To address this limitation, this paper proposes a novel post-hoc framework for generating semantic explanations of neurons with large foundation models, without requiring human intervention or prior knowledge. Experiments are conducted with both qualitative and quantitative analysis to verify the effectiveness of our proposed approach.
Cite
Text
Zhao et al. "Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30537Markdown
[Zhao et al. "Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/zhao2024aaai-automated/) doi:10.1609/AAAI.V38I21.30537BibTeX
@inproceedings{zhao2024aaai-automated,
title = {{Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract)}},
author = {Zhao, Chenxu and Qian, Wei and Shi, Yucheng and Huai, Mengdi and Liu, Ninghao},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23712-23713},
doi = {10.1609/AAAI.V38I21.30537},
url = {https://mlanthology.org/aaai/2024/zhao2024aaai-automated/}
}