Interpretability
Hierarchical Network Dissection
Introduced by Teotia et al. in Interpreting Face Inference Models using Hierarchical Network DissectionHierarchical 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.
Source: Interpreting Face Inference Models using Hierarchical Network Dissection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
