Deeper Interpretability of Deep Networks

11/19/2018
by   Tian Xu, et al.
14

Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization. There is an increasing demand for explainable AI as these systems are deployed in the real world. However, understanding the information represented and processed in CNNs remains in most cases challenging. Within this paper, we explore the use of new information theoretic techniques developed in the field of neuroscience to enable novel understanding of how a CNN represents information. We trained a 10-layer ResNet architecture to identify 2,000 face identities from 26M images generated using a rigorously controlled 3D face rendering model that produced variations of intrinsic (i.e. face morphology, gender, age, expression and ethnicity) and extrinsic factors (i.e. 3D pose, illumination, scale and 2D translation). With our methodology, we demonstrate that unlike human's network overgeneralizes face identities even with extreme changes of face shape, but it is more sensitive to changes of texture. To understand the processing of information underlying these counterintuitive properties, we visualize the features of shape and texture that the network processes to identify faces. Then, we shed a light into the inner workings of the black box and reveal how hidden layers represent these features and whether the representations are invariant to pose. We hope that our methodology will provide an additional valuable tool for interpretability of CNNs.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 7

page 8

page 9

research
05/02/2020

An Information-theoretic Visual Analysis Framework for Convolutional Neural Networks

Despite the great success of Convolutional Neural Networks (CNNs) in Com...
research
10/12/2019

How are attributes expressed in face DCNNs?

As deep networks become increasingly accurate at recognizing faces, it i...
research
04/09/2015

What Do Deep CNNs Learn About Objects?

Deep convolutional neural networks learn extremely powerful image repres...
research
03/17/2018

SeqFace: Make full use of sequence information for face recognitio

Deep convolutional neural networks (CNNs) have greatly improved the Face...
research
04/18/2018

Understanding Convolutional Neural Network Training with Information Theory

Using information theoretic concepts to understand and explore the inner...
research
03/20/2023

Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images

The function of constructing the hierarchy of objects is important to th...
research
10/16/2022

Demystifying CNNs for Images by Matched Filters

The success of convolution neural networks (CNN) has been revolutionisin...

Please sign up or login with your details

Forgot password? Click here to reset