Trainable Noise Model as an XAI evaluation method: application on Sobol
for remote sensing image segmentation
- URL: http://arxiv.org/abs/2310.01828v2
- Date: Sat, 25 Nov 2023 13:35:34 GMT
- Title: Trainable Noise Model as an XAI evaluation method: application on Sobol
for remote sensing image segmentation
- Authors: Hossein Shreim, Abdul Karim Gizzini and Ali J. Ghandour
- Abstract summary: This paper adapts the gradient-free Sobol XAI method for semantic segmentation.
A benchmark analysis is conducted to evaluate and compare performance of three XAI methods.
- Score: 0.5735035463793009
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: eXplainable Artificial Intelligence (XAI) has emerged as an essential
requirement when dealing with mission-critical applications, ensuring
transparency and interpretability of the employed black box AI models. The
significance of XAI spans various domains, from healthcare to finance, where
understanding the decision-making process of deep learning algorithms is
essential. Most AI-based computer vision models are often black boxes; hence,
providing explainability of deep neural networks in image processing is crucial
for their wide adoption and deployment in medical image analysis, autonomous
driving, and remote sensing applications. Recently, several XAI methods for
image classification tasks have been introduced. On the contrary, image
segmentation has received comparatively less attention in the context of
explainability, although it is a fundamental task in computer vision
applications, especially in remote sensing. Only some research proposes
gradient-based XAI algorithms for image segmentation. This paper adapts the
recent gradient-free Sobol XAI method for semantic segmentation. To measure the
performance of the Sobol method for segmentation, we propose a quantitative XAI
evaluation method based on a learnable noise model. The main objective of this
model is to induce noise on the explanation maps, where higher induced noise
signifies low accuracy and vice versa. A benchmark analysis is conducted to
evaluate and compare performance of three XAI methods, including Seg-Grad-CAM,
Seg-Grad-CAM++ and Seg-Sobol using the proposed noise-based evaluation
technique. This constitutes the first attempt to run and evaluate XAI methods
using high-resolution satellite images.
Related papers
- Underwater SONAR Image Classification and Analysis using LIME-based Explainable Artificial Intelligence [0.0]
This paper explores the application of the eXplainable Artificial Intelligence (XAI) tool to interpret the underwater image classification results.
An extensive analysis of transfer learning techniques for image classification using benchmark Convolutional Neural Network (CNN) architectures is carried out.
XAI techniques highlight interpretability of the results in a more human-compliant way, thus boosting our confidence and reliability.
arXiv Detail & Related papers (2024-08-23T04:54:18Z) - Explainable AI for Enhancing Efficiency of DL-based Channel Estimation [1.0136215038345013]
Support of artificial intelligence based decision-making is a key element in future 6G networks.
In such applications, using AI as black-box models is risky and challenging.
We propose a novel-based XAI-CHEST framework that is oriented toward channel estimation in wireless communications.
arXiv Detail & Related papers (2024-07-09T16:24:21Z) - RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection [60.960988614701414]
RIGID is a training-free and model-agnostic method for robust AI-generated image detection.
RIGID significantly outperforms existing trainingbased and training-free detectors.
arXiv Detail & Related papers (2024-05-30T14:49:54Z) - DSEG-LIME: Improving Image Explanation by Hierarchical Data-Driven Segmentation [2.355460994057843]
LIME (Local Interpretable Model-agnostic Explanations) is a well-known XAI framework for image analysis.
We introduce DSEG-LIME (Data-Driven LIME), featuring a data-driven segmentation for human-recognized feature generation.
We benchmark DSEG-LIME on pre-trained models with images from the ImageNet dataset.
arXiv Detail & Related papers (2024-03-12T15:13:12Z) - Extending CAM-based XAI methods for Remote Sensing Imagery Segmentation [7.735470452949379]
We introduce a new XAI evaluation methodology and metric based on "Entropy" to measure the model uncertainty.
We show that using Entropy to monitor the model uncertainty in segmenting the pixels within the target class is more suitable.
arXiv Detail & Related papers (2023-10-03T07:01:23Z) - Improving Human-Object Interaction Detection via Virtual Image Learning [68.56682347374422]
Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects.
In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL)
A novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images.
arXiv Detail & Related papers (2023-08-04T10:28:48Z) - Two Approaches to Supervised Image Segmentation [55.616364225463066]
The present work develops comparison experiments between deep learning and multiset neurons approaches.
The deep learning approach confirmed its potential for performing image segmentation.
The alternative multiset methodology allowed for enhanced accuracy while requiring little computational resources.
arXiv Detail & Related papers (2023-07-19T16:42:52Z) - Optimizing Explanations by Network Canonization and Hyperparameter
Search [74.76732413972005]
Rule-based and modified backpropagation XAI approaches often face challenges when being applied to modern model architectures.
Model canonization is the process of re-structuring the model to disregard problematic components without changing the underlying function.
In this work, we propose canonizations for currently relevant model blocks applicable to popular deep neural network architectures.
arXiv Detail & Related papers (2022-11-30T17:17:55Z) - Adaptive Convolutional Dictionary Network for CT Metal Artifact
Reduction [62.691996239590125]
We propose an adaptive convolutional dictionary network (ACDNet) for metal artifact reduction.
Our ACDNet can automatically learn the prior for artifact-free CT images via training data and adaptively adjust the representation kernels for each input CT image.
Our method inherits the clear interpretability of model-based methods and maintains the powerful representation ability of learning-based methods.
arXiv Detail & Related papers (2022-05-16T06:49:36Z) - Rethinking of the Image Salient Object Detection: Object-level Semantic
Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter [62.26677215668959]
We propose a lightweight, weakly supervised deep network to coarsely locate semantically salient regions.
We then fuse multiple off-the-shelf deep models on these semantically salient regions as the pixel-wise saliency refinement.
Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.
arXiv Detail & Related papers (2020-08-10T07:12:43Z) - Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI [12.680653816836541]
We propose a ground truth based evaluation framework for XAI methods based on the CLEVR visual question answering task.
Our framework provides a (1) selective, (2) controlled and (3) realistic testbed for the evaluation of neural network explanations.
arXiv Detail & Related papers (2020-03-16T14:43:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.