These do not Look Like Those: An Interpretable Deep Learning Model for Image Recognition

Abstract

Interpretation of the reasoning process of a prediction made by a deep learning model is always desired. However, when it comes to the predictions of a deep learning model that directly impacts on the lives of people then the interpretation becomes a necessity. In this paper, we introduce a deep learning model: negative-positive prototypical part network (NP-ProtoPNet). This model attempts to imitate human reasoning for image recognition while comparing the parts of a test image with the corresponding parts of the images from known classes. We demonstrate our model on the dataset of chest X-ray images of Covid-19 patients, pneumonia patients and normal people. The accuracy and precision that our model receives is on par with the best performing non-interpretable deep learning models.INDEX TERMS Covid-19, pneumonia, image recognition, X-ray, prototypical part.

Object or Background: An Interpretable Deep Learning Model for COVID-19 Detection from CT-Scan Images

“…A substantial improvement over the above work was made by Chen et al with the development of their model ProtoPNet [ 16 ]. The models Gen-ProtoPNet [ 17 ] and NP-ProtoPNet [ 18 ] are close variations of ProtoPNet.…”

“…So, we propose an interpretable deep learning model: pseudo prototypical part network (Ps-ProtoPNet), and experiment it over the dataset of CT-scan images, see Section 2.4 . Ps-ProtoPNet is closely related to ProtoPNet [ 16 ], Gen-ProtoPNet [ 17 ] and NP-Proto-PNet [ 18 ], but strikingly different from these models.…”

An Interpretable Deep Learning Model for Covid-19 Detection With Chest X-Ray Images

“…As mentioned in the introduction, many networks have been emerged to classify the X-ray images of Covid-19 patients along with X-ray images of normal people and pneumonia patients, see [4], [12], [22], [23], [25], [36], [37], [40], [41], [58]. A study summarizes some papers on Covid-19, and it points out some problems, such as: lack of reliable and adequate amount of data for deep learning algorithms [5].…”

“…The objective of this work is to find an interpretable method to do image classification so that we can tell why an image is classified in a certain way. In this work, we introduce an interpretable deep learning model: generalized prototypical part network (Gen-ProtoPNet), and experiment it over the dataset of three different classes of Xrays, see Section V. Gen-ProtoPNet is a close variation of ProtoPNet [7] and NP-ProtoPNet [41]. To predict the class of a test image, ProtoPNet calculates the similarity scores between learned prototypical parts (with square spacial di-mensions 1 × 1) of images from each class and parts of the test image using L2 distance function.…”

“…In this work, we introduce an interpretable deep learning model: generalized prototypical part network (Gen-ProtoPNet), and experiment it over the dataset of three different classes of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$X$ \end{document} -rays, see Section V . Gen-ProtoPNet is a close variation of ProtoPNet [7] and NP-ProtoPNet [41] . To predict the class of a test image, ProtoPNet calculates the similarity scores between learned prototypical parts (with square spacial dimensions \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$1 \times 1$ \end{document} ) of images from each class and parts of the test image using \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$L2$ \end{document} distance function.…”