Network Dissection

2000년 도입 · 논문 11편에서 사용

Network Dissection is an interpretability method for CNNs that evaluates the alignment between individual hidden units and a set of visual semantic concepts. By identifying the best alignments, units are given human interpretable labels across a range of objects, parts, scenes, textures, materials, and colors. The measurement of interpretability proceeds in three steps: - Identify a broad set of human-labeled visual concepts. - Gather the response of the hidden variables to known concepts. - Quantify alignment of hidden variable−concept pairs.

출처: Interpreting Deep Visual Representations via Network Dissection

소개 논문: Interpreting Deep Visual Representations via Network Dissection