What do CNN neurons learn: Visualization Clustering

10/18/2020
by   Haoyue Dai, et al.
0

In recent years convolutional neural networks (CNN) have shown striking progress in various tasks. However, despite the high performance, the training and prediction process remains to be a black box, leaving it a mystery to extract what neurons learn in CNN. In this paper, we address the problem of interpreting a CNN from the aspects of the input image's focus and preference, and the neurons' domination, activation and contribution to a concrete final prediction. Specifically, we use two techniques - visualization and clustering - to tackle the problems above. Visualization means the method of gradient descent on image pixel, and in clustering section two algorithms are proposed to cluster respectively over image categories and network neurons. Experiments and quantitative analyses have demonstrated the effectiveness of the two methods in explaining the question: what do neurons learn.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

research
03/06/2023

Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks

Adversarial attacks on a convolutional neural network (CNN) – injecting ...
research
08/31/2016

Towards Transparent AI Systems: Interpreting Visual Question Answering Models

Deep neural networks have shown striking progress and obtained state-of-...
research
07/30/2017

Towards Visual Explanations for Convolutional Neural Networks via Input Resampling

The predictive power of neural networks often costs model interpretabili...
research
12/31/2021

PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability

In this paper we introduce a new problem within the growing literature o...
research
05/19/2017

CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data

Given a large unlabeled set of images, how to efficiently and effectivel...
research
05/02/2022

Revisiting Gaussian Neurons for Online Clustering with Unknown Number of Clusters

Despite the recent success of artificial neural networks, more biologica...
research
06/18/2023

Learn to Enhance the Negative Information in Convolutional Neural Network

This paper proposes a learnable nonlinear activation mechanism specifica...

Please sign up or login with your details

Forgot password? Click here to reset