Hierarchical Network Dissection

2000년 도입 · 논문 1편에서 사용

Hierarchical Network Dissection is a pipeline for interpreting the internal representation of face-centric inference models. Using a probabilistic formulation, Hierarchical Network Dissection pairs units of the model with concepts in a "Face Dictionary" (a collection of facial concepts with corresponding sample images). Interpretable units are discovered in a convolution layer through HND to identify multiple instances of unit-concept affinity. The pipeline is inspired by Network Dissection, an interpretability model for object-centric and scene-centric models.

출처: Interpreting Face Inference Models using Hierarchical Network Dissection

소개 논문: Interpreting Face Inference Models using Hierarchical Network Dissection