In recent years, there has been an increasing trend of applying artificial intelligence in many different fields, which has a profound and direct impact on human life. Consequently, this raises the need to understand the principles of model making predictions. Since most current high-precision models are black boxes, neither the AI scientist nor the end-user profoundly understands what is happening inside these models. Therefore, many algorithms are studied to explain AI models, especially those in the image classification problem in computer vision such as LIME, CAM, GradCAM. However, these algorithms still have limitations, such as LIME's long execution time and CAM's confusing interpretation of concreteness and clarity. Therefore, in this paper, we will propose a new method called Segmentation - Class Activation Mapping (SeCAM)/ This method combines the advantages of these algorithms above while at simultaneously overcoming their disadvantages. We tested this algorithm with various models, including ResNet50, InceptionV3, and VGG16 from ImageNet Large Scale Visual Recognition Challenge (ILSVRC) data set. Outstanding results were achieved when the algorithm has met all the requirements for a specific explanation in a remarkably short space of time.
Phong X. NGUYEN
The University of Tokyo
Hung Q. CAO
FPT Software
Khang V. T. NGUYEN
FPT Software
Hung NGUYEN
FPT Software
Takehisa YAIRI
The University of Tokyo
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Phong X. NGUYEN, Hung Q. CAO, Khang V. T. NGUYEN, Hung NGUYEN, Takehisa YAIRI, "SeCAM: Tightly Accelerate the Image Explanation via Region-Based Segmentation" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 8, pp. 1401-1417, August 2022, doi: 10.1587/transinf.2021EDP7205.
Abstract: In recent years, there has been an increasing trend of applying artificial intelligence in many different fields, which has a profound and direct impact on human life. Consequently, this raises the need to understand the principles of model making predictions. Since most current high-precision models are black boxes, neither the AI scientist nor the end-user profoundly understands what is happening inside these models. Therefore, many algorithms are studied to explain AI models, especially those in the image classification problem in computer vision such as LIME, CAM, GradCAM. However, these algorithms still have limitations, such as LIME's long execution time and CAM's confusing interpretation of concreteness and clarity. Therefore, in this paper, we will propose a new method called Segmentation - Class Activation Mapping (SeCAM)/ This method combines the advantages of these algorithms above while at simultaneously overcoming their disadvantages. We tested this algorithm with various models, including ResNet50, InceptionV3, and VGG16 from ImageNet Large Scale Visual Recognition Challenge (ILSVRC) data set. Outstanding results were achieved when the algorithm has met all the requirements for a specific explanation in a remarkably short space of time.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7205/_p
Copy
@ARTICLE{e105-d_8_1401,
author={Phong X. NGUYEN, Hung Q. CAO, Khang V. T. NGUYEN, Hung NGUYEN, Takehisa YAIRI, },
journal={IEICE TRANSACTIONS on Information},
title={SeCAM: Tightly Accelerate the Image Explanation via Region-Based Segmentation},
year={2022},
volume={E105-D},
number={8},
pages={1401-1417},
abstract={In recent years, there has been an increasing trend of applying artificial intelligence in many different fields, which has a profound and direct impact on human life. Consequently, this raises the need to understand the principles of model making predictions. Since most current high-precision models are black boxes, neither the AI scientist nor the end-user profoundly understands what is happening inside these models. Therefore, many algorithms are studied to explain AI models, especially those in the image classification problem in computer vision such as LIME, CAM, GradCAM. However, these algorithms still have limitations, such as LIME's long execution time and CAM's confusing interpretation of concreteness and clarity. Therefore, in this paper, we will propose a new method called Segmentation - Class Activation Mapping (SeCAM)/ This method combines the advantages of these algorithms above while at simultaneously overcoming their disadvantages. We tested this algorithm with various models, including ResNet50, InceptionV3, and VGG16 from ImageNet Large Scale Visual Recognition Challenge (ILSVRC) data set. Outstanding results were achieved when the algorithm has met all the requirements for a specific explanation in a remarkably short space of time.},
keywords={},
doi={10.1587/transinf.2021EDP7205},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - SeCAM: Tightly Accelerate the Image Explanation via Region-Based Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 1401
EP - 1417
AU - Phong X. NGUYEN
AU - Hung Q. CAO
AU - Khang V. T. NGUYEN
AU - Hung NGUYEN
AU - Takehisa YAIRI
PY - 2022
DO - 10.1587/transinf.2021EDP7205
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2022
AB - In recent years, there has been an increasing trend of applying artificial intelligence in many different fields, which has a profound and direct impact on human life. Consequently, this raises the need to understand the principles of model making predictions. Since most current high-precision models are black boxes, neither the AI scientist nor the end-user profoundly understands what is happening inside these models. Therefore, many algorithms are studied to explain AI models, especially those in the image classification problem in computer vision such as LIME, CAM, GradCAM. However, these algorithms still have limitations, such as LIME's long execution time and CAM's confusing interpretation of concreteness and clarity. Therefore, in this paper, we will propose a new method called Segmentation - Class Activation Mapping (SeCAM)/ This method combines the advantages of these algorithms above while at simultaneously overcoming their disadvantages. We tested this algorithm with various models, including ResNet50, InceptionV3, and VGG16 from ImageNet Large Scale Visual Recognition Challenge (ILSVRC) data set. Outstanding results were achieved when the algorithm has met all the requirements for a specific explanation in a remarkably short space of time.
ER -