A review of visualisation-as-explanation techniques for convolutional neural networks and their evaluation

Mohamed, Elhassan; Sirlantzis, Konstantinos; Howells, Gareth

doi:10.1016/j.displa.2022.102239

Cited by 34 publications

(12 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To combine LRP and DTD, LRP can be thought of as providing the framework for propagating relevance through a network, whereas DTD provides the means for approximating the complex non-linear functions used by the network. LRP and DTD may lead to overcoming the limitations of saliency maps and provide more accurate explanations [ 75 ].…”

Section: Introduction Of the Explainable Ai Method: A Brief Overviewmentioning

confidence: 99%

Survey of Explainable AI Techniques in Healthcare

Chaddad

Peng

et al. 2023

Sensors

214

View full text Add to dashboard Cite

Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the medical field, any judgment or decision is fraught with risk. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient’s symptoms and/or an examination. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.

show abstract

Section: Introduction Of the Explainable Ai Method: A Brief Overviewmentioning

confidence: 99%

Survey of Explainable AI Techniques in Healthcare

Chaddad

Peng

et al. 2023

Sensors

214

View full text Add to dashboard Cite

show abstract

“…A different approach is necessary in the case of CNNs. For example, in the case of a CNN that classify images into different categories, a common approach is to use saliency maps, which measure the support that different groups of pixels in an image provides for a particular class ( Mohamed et al 2022 ). This is implemented by feeding the CNN an image of a particular class and using visualization techniques to generate heatmaps overlayed on the original image; the image elements that are being used by the CNN to identify the class are highlighted in red.…”

Section: Interpretable Machine Learningmentioning

confidence: 99%

Deep Learning in Population Genetics

Korfmann

Gaggiotti

Fumagalli

2023

Genome Biology and Evolution

View full text Add to dashboard Cite

Population genetics is transitioning into a data-driven discipline thanks to the availability of large-scale genomic data and the need to study increasingly complex evolutionary scenarios. With likelihood and Bayesian approaches becoming either intractable or computationally unfeasible, machine learning, and in particular deep learning, algorithms are emerging as popular techniques for population genetic inferences. These approaches rely on algorithms that learn non-linear relationships between the input data and the model parameters being estimated through representation learning from training data sets. Deep learning algorithms currently employed in the field comprise discriminative and generative models with fully connected, con volutional, or recurrent layers. Additionally, a wide range of powerful simulators to generate training data under complex scenarios are now available. The application of deep learning to empirical data sets mostly replicates previous findings of demography reconstruction and signals of natural selection in model organisms. To showcase the feasibility of deep learning to tackle new challenges, we designed a branched architecture to detect signals of recent balancing selection from temporal haplotypic data, which exhibited good predictive performance on simulated data. Investigations on the interpretability of neural networks, their robustness to uncertain training data, and creative representation of population genetic data, will provide further opportunities for technological advancements in the field.

show abstract

“…To validate the reliability of the best single-head YOLO V3 detector, novel techniques for visualising the network decisions are applied. The proposed techniques can be applied to classification tasks like other visualisation techniques [ 54 ]. However, applying them to different tasks, such as object detection, is a novel contribution.…”

Section: Visualisation Of Detector Predictionsmentioning

confidence: 99%

Optimisation of Deep Learning Small-Object Detectors with Novel Explainable Verification

Mohamed

Sirlantzis

Howells

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, we present a novel methodology based on machine learning for identifying the most appropriate from a set of available state-of-the-art object detectors for a given application. Our particular interest is to develop a road map for identifying verifiably optimal selections, especially for challenging applications such as detecting small objects in a mixed-size object dataset. State-of-the-art object detection systems often find the localisation of small-size objects challenging since most are usually trained on large-size objects. These contain abundant information as they occupy a large number of pixels relative to the total image size. This fact is normally exploited by the model during training and inference processes. To dissect and understand this process, our approach systematically examines detectors’ performances using two very distinct deep convolutional networks. The first is the single-stage YOLO V3 and the second is the double-stage Faster R-CNN. Specifically, our proposed method explores and visually illustrates the impact of feature extraction layers, number of anchor boxes, data augmentation, etc., utilising ideas from the field of explainable Artificial Intelligence (XAI). Our results, for example, show that multi-head YOLO V3 detectors trained using augmented data produce better performance even with a fewer number of anchor boxes. Moreover, robustness regarding the detector’s ability to explain how a specific decision was reached is investigated using different explanation techniques. Finally, two new visualisation techniques are proposed, WS-Grad and Concat-Grad, for identifying explanation cues of different detectors. These are applied to specific object detection tasks to illustrate their reliability and transparency with respect to the decision process. It is shown that the proposed techniques can result in high resolution and comprehensive heatmaps of the image areas, significantly affecting detector decisions as compared to the state-of-the-art techniques tested.

show abstract

A review of visualisation-as-explanation techniques for convolutional neural networks and their evaluation

Cited by 34 publications

References 43 publications

Survey of Explainable AI Techniques in Healthcare

Survey of Explainable AI Techniques in Healthcare

Deep Learning in Population Genetics

Optimisation of Deep Learning Small-Object Detectors with Novel Explainable Verification

Contact Info

Product

Resources

About