Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation

08/06/2019
by   Brian Kenji Iwana, et al.
30

Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relevance of the output probability to the input image. Through qualitative and quantitative analysis, we demonstrate that SGLRP can successfully localize and attribute the regions on input images which contribute to a target object's classification. We show that the proposed method excels at discriminating the target objects class from the other possible objects in the images. We confirm that SGLRP performs better than existing Layer-wise Relevance Propagation (LRP) based methods and can help in the understanding of the decision process of CNNs.

READ FULL TEXT

page 1

page 6

page 7

page 11

research
12/22/2017

Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation

Despite the tremendous achievements of deep convolutional neural network...
research
12/05/2018

Understanding Individual Decisions of CNNs via Contrastive Backpropagation

A number of backpropagation-based approaches such as DeConvNets, vanilla...
research
03/21/2023

Unlocking Layer-wise Relevance Propagation for Autoencoders

Autoencoders are a powerful and versatile tool often used for various pr...
research
03/04/2020

On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Deep convolutional neural networks (CNNs) trained with logistic and soft...
research
11/16/2016

VisualBackProp: efficient visualization of CNNs

This paper proposes a new method, that we call VisualBackProp, for visua...
research
03/21/2016

Controlling Explanatory Heatmap Resolution and Semantics via Decomposition Depth

We present an application of the Layer-wise Relevance Propagation (LRP) ...
research
07/17/2018

Layer-wise Relevance Propagation for Explainable Recommendations

In this paper, we tackle the problem of explanations in a deep-learning ...

Please sign up or login with your details

Forgot password? Click here to reset