DeepVID: Deep Visual Interpretation and Diagnosis for Image Classifiers via Knowledge Distillation

• Published in: IEEE transactions on visualization and computer graphics Vol. 25; no. 6; pp. 2168 - 2180
• Main Authors: Wang, Junpeng, Gou, Liang, Zhang, Wei, Yang, Hao, Shen, Han-Wei
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytical models; Artificial neural networks; Classifiers; Data models; Deep learning; Deep neural networks; Diagnosis; Distillation; generative model; knowledge distillation; Knowledge management; Machine learning; Medical imaging; model interpretation; Neural networks; Safety critical; Semantics; Training; Visual analytics

Deep Neural Networks (DNNs) have been extensively used in multiple disciplines due to their superior performance. However, in most cases, DNNs are considered as black-boxes and the interpretation of their internal working mechanism is usually challenging. Given that model trust is often built on the...