Loading…

MemeNet: Toward a Reliable Local Projection for Image Recognition via Semantic Featurization

When we recognize images with the help of Artificial Neural Networks (ANNs), we often wonder how they make decisions. A widely accepted solution is to point out local features as decisive evidence. A question then arises: Can local features in the latent space of an ANN explain the model output to s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2024, Vol.33, p.1670-1682
Main Authors: Tang, Jiacheng, Kang, Qi, Zhou, Mengchu, Yin, Hao, Yao, Siya
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:When we recognize images with the help of Artificial Neural Networks (ANNs), we often wonder how they make decisions. A widely accepted solution is to point out local features as decisive evidence. A question then arises: Can local features in the latent space of an ANN explain the model output to some extent? In this work, we propose a modularized framework named MemeNet that can construct a reliable surrogate from a Convolutional Neural Network (CNN) without changing its perception. Inspired by the idea of time series classification, this framework recognizes images in two steps. First, local representations named memes are extracted from the activation map of a CNN model. Then an image is transformed into a series of understandable features. Experimental results show that MemeNet can achieve accuracy comparable to most models' through a set of reliable features and a simple classifier. Thus, it is a promising interface to use the internal dynamics of CNN, which represents a novel approach to constructing reliable models.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2024.3359331