Robustness evaluation on different training state of a CNN model
Abstract: Convolutional neural networks (CNNs) have proved to be successful in many applications such as image processing. However, even imperceptible perturbations applied to the images can make the neural network performance unreliable. To guarantee an accurate performance in safety critical fields, it is necessary to assess the robustness of CNN solutions before launching. Adversarial attack is a machine learning approach to generate perturbations on real samples to detect the vulnerability of CNN. In this paper, we will use an adversarial attack technique to evaluate a CNN at different training states. The model was trained to perform surgical tool classification task, which was applied to recognize surgical tool in Cholecystectomy to further analyze surgical process. The experiments demonstrate the relation between training states and robustness, i.e. the robustness improved at higher training states, especially for some particular classes. In future work, additional training with generated adversarial images may improve the robustness of the model.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
Robustness evaluation on different training state of a CNN model ; volume:8 ; number:2 ; year:2022 ; pages:497-500 ; extent:4
Current directions in biomedical engineering ; 8, Heft 2 (2022), 497-500 (gesamt 4)
- Creator
- DOI
-
10.1515/cdbme-2022-1127
- URN
-
urn:nbn:de:101:1-2022090315340993091515
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
- 15.08.2025, 7:35 AM CEST
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Ding, Ning
- Möller, Knut
Other Objects (12)
Using adaptive learning rate to generate adversarial images
The Image flip effect on a CNN model classification
Generating adversarial images to monitor the training state of a CNN model
The effect of feature space separation at different training states of CNN
Feature space separation by conformity loss driven training of CNN
Generate adversarial images with gradient search
Minimally Distorted Adversarial Images with a Step-Adaptive Iterative Fast Gradient Sign Method
AI-based solutions in endoscopy image processing : robustness and certification
Fourier Series Model for Facial Feature Point Land-Marking
DACAPO : Data fusion in operating room
Predicting Surgical Phases using CNN-NARX Neural Network
Analysis of expansion within a pressure inflated section of an urethral stricture model
Using adaptive learning rate to generate adversarial images
The Image flip effect on a CNN model classification
Generating adversarial images to monitor the training state of a CNN model
The effect of feature space separation at different training states of CNN
Feature space separation by conformity loss driven training of CNN
Generate adversarial images with gradient search
Minimally Distorted Adversarial Images with a Step-Adaptive Iterative Fast Gradient Sign Method
AI-based solutions in endoscopy image processing : robustness and certification
Fourier Series Model for Facial Feature Point Land-Marking
DACAPO : Data fusion in operating room
Predicting Surgical Phases using CNN-NARX Neural Network
Analysis of expansion within a pressure inflated section of an urethral stricture model
Using adaptive learning rate to generate adversarial images
The Image flip effect on a CNN model classification
Generating adversarial images to monitor the training state of a CNN model
The effect of feature space separation at different training states of CNN
Feature space separation by conformity loss driven training of CNN
Generate adversarial images with gradient search
Minimally Distorted Adversarial Images with a Step-Adaptive Iterative Fast Gradient Sign Method
AI-based solutions in endoscopy image processing : robustness and certification
Fourier Series Model for Facial Feature Point Land-Marking
DACAPO : Data fusion in operating room
Predicting Surgical Phases using CNN-NARX Neural Network