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.
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
School of Computing, University of Georgia(佐治亚大学计算学院);Department of Data Science, New Jersey Institute of Technology(新泽西理工学院数据科学系);Department of Computer Science, New York University(纽约大学计算机科学系)
Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
University of Waterloo(多伦多大学);Perimeter Institute for Theoretical Physics(理论物理研究所);Homes Plus Magazine Inc.(Homes Plus 杂志公司);University of Toronto(多伦多大学)