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

By Junpeng Wang, Liang Gou, Hao Yang, Han-Wei Shen. 2019

120 citations recorded by the source corpus.

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 understanding of how a model works, the interpretation of DNNs becomes more important, especially in safety-critical applications (e.g., medical diagnosis, autonomous driving). In this paper, we propose DeepVID, a Deep learning approach to Visually Interpret and Diagnose DNN models, especially image classifiers. In detail, we train a small locally-faithful model to mimic the behavior of an original cumbersome DNN around a particular data instance of interest, and the local model is sufficiently simple such that it can be visually interpreted (e.g., a linear model). Knowledge distillation is used to transfer the knowledge from the cumbersome DNN to the small model, and a deep generative model (i.e., variational auto-encoder) is used to generate neighbors around the instance of interest. Those neighbors, which come with small feature variances and semantic meanings, can effectively probe the DNN's behaviors around the interested instance and help the small model to learn those behaviors. Through comprehensive evaluations, as well as case studies conducted together with deep learning experts, we validate the effectiveness of DeepVID.

Subfields: Artificial Intelligence, Biophysics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Sungho Shin
3. Yoonho Boo
4. Jianping Gou
5. Wonyong Sung
6. S. Maybank
7. Baosheng Yu
8. Sajid Anwar

In Biophysics

1. Dacheng Tao

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Jianping Gou
3. S. Maybank
4. Wonyong Sung
5. Baosheng Yu
6. Sungho Shin
7. Yoonho Boo
8. Luc Van Gool

Citations in the corpus

• Knowledge Distillation: A Survey (2020, methodology): “…extended to other visual recognition applications, including face recognition (Luo et al. 2016; Kong et al. 2019; Yan et al. 2019; Ge et al. 2018; Wang et al. 2018b, 2019c; Duong et al. 2019; Wu et al. 2020; Wang et al. 2017; Zhang et al. 2020b; Wang et al. 2020b), image/video segmentation (He…”
• Empirical Analysis of Knowledge Distillation Technique for Optimization of Quantized Deep Neural Networks (2019, background): “Leveraging the knowledge contained in previously trained networks has attracted a lot of attention in a variety of applications for model compression (Tang, Wang, and Zhang 2016; Song et al. 2018; Asami et al. 2017; Wang et al. 2019).”
• Knowledge Distillation for Optimization of Quantized Deep Neural Networks (2019, background): “Leveraging the knowledge contained in previously trained networks has attracted attention in many applications for model compression [8, 9, 10, 11] and learning algorithms [12, 13, 14, 15].”