arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.16475cs.LGcs.CV
收藏

深度学习训练中的概念演化:统一解释框架与若干发现

Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries

Georgia Tech(佐治亚理工学院)

Haekyu Park, Seongmin Lee, Benjamin Hoover, Austin P. Wright, Omar Shaikh, Rahul Duggal, Nilaksh Das, Kevin Li, Judy Hoffman, Duen Horng Chau

AI总结:

针对现有DNN解释多聚焦训练后阶段的空白,提出统一解释框架ConceptEvo,含统一语义空间生成、概念演化发现量化两项技术,经实验验证有效且适配多种经典与现代DNN架构。

摘要:

我们提出ConceptEvo,一种用于深度神经网络(DNN)的统一解释框架,可揭示训练过程中所学概念的产生与演化。现有DNN解释研究主要聚焦训练后解释,我们的工作填补了这一关键空白。ConceptEvo有两项新颖技术贡献:(1)生成统一语义空间的算法,可对训练中不同模型进行并排比较;(2)发现并量化类别预测所需重要概念演化的算法。通过大规模人类评估与定量实验,我们证明ConceptEvo能成功识别不同模型间的概念演化,这些演化不仅人类可理解,且对类别预测至关重要。ConceptEvo既适用于ConvNeXt等现代DNN架构,也适用于VGG、InceptionV3等经典DNN。

英文摘要:

We present ConceptEvo, a unified interpretation framework for deep neural networks (DNNs) that reveals the inception and evolution of learned concepts during training. Our work addresses a critical gap in DNN interpretation research, as existing methods primarily focus on post-training interpretation. ConceptEvo introduces two novel technical contributions: (1) an algorithm that generates a unified semantic space, enabling side-by-side comparison of different models during training, and (2) an algorithm that discovers and quantifies important concept evolutions for class predictions. Through a large-scale human evaluation and quantitative experiments, we demonstrate that ConceptEvo successfully identifies concept evolutions across different models, which are not only comprehensible to humans but also crucial for class predictions. ConceptEvo is applicable to both modern DNN architectures, such as ConvNeXt, and classic DNNs, such as VGGs and InceptionV3.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑