A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification

Mascarenhas, Sheldon; Agarwal, Mukul

doi:10.1109/centcon52345.2021.9687944

Cited by 244 publications

(76 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This new observation supports the importance of building large and diverse image datasets in developing CAD schemes based on deep learning technologies. In addition, compared to our own previous studies that used other deep learning models, including an AlexNet [ 30 ] and a VGG-16 [ 29 ], we also observed that ResNet50 yields a higher accuracy in breast lesion classification, which supports conclusions previously reported by other researchers [ 23 , 24 ].…”

Section: Discussionsupporting

confidence: 91%

“…Among them, ResNet50 yields the highest classification accuracy [ 23 ]. Another study compared VGG-16, VGG-19, and ResNet50 and concluded that ResNet 50 was the best architecture framework for image classification task with the highest accuracy and efficiency to train [ 24 ]. Thus, in this study we selected the popular image classification architecture of residual net architecture (ResNet50) to build a deep transfer learning model used in our CAD scheme.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Comparison of Computer-Aided Diagnosis Schemes Optimized Using Radiomics and Deep Transfer Learning Methods

et al. 2022

View full text Add to dashboard Cite

Objective: Radiomics and deep transfer learning are two popular technologies used to develop computer-aided detection and diagnosis (CAD) schemes of medical images. This study aims to investigate and to compare the advantages and the potential limitations of applying these two technologies in developing CAD schemes. Methods: A relatively large and diverse retrospective dataset including 3000 digital mammograms was assembled in which 1496 images depicted malignant lesions and 1504 images depicted benign lesions. Two CAD schemes were developed to classify breast lesions. The first scheme was developed using four steps namely, applying an adaptive multi-layer topographic region growing algorithm to segment lesions, computing initial radiomics features, applying a principal component algorithm to generate an optimal feature vector, and building a support vector machine classifier. The second CAD scheme was built based on a pre-trained residual net architecture (ResNet50) as a transfer learning model to classify breast lesions. Both CAD schemes were trained and tested using a 10-fold cross-validation method. Several score fusion methods were also investigated to classify breast lesions. CAD performances were evaluated and compared by the areas under the ROC curve (AUC). Results: The ResNet50 model-based CAD scheme yielded AUC = 0.85 ± 0.02, which was significantly higher than the radiomics feature-based CAD scheme with AUC = 0.77 ± 0.02 (p < 0.01). Additionally, the fusion of classification scores generated by the two CAD schemes did not further improve classification performance. Conclusion: This study demonstrates that using deep transfer learning is more efficient to develop CAD schemes and it enables a higher lesion classification performance than CAD schemes developed using radiomics-based technology.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Methodsmentioning

confidence: 99%

A Comparison of Computer-Aided Diagnosis Schemes Optimized Using Radiomics and Deep Transfer Learning Methods

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In Table 3, we compare EyeDAS's performance to that of two other approaches: (1) baseline models based on the state-of-the-art pre-trained image classifiers (i.e., VGG16, VGG19 and Resnet50 [22]); we utilize the known transfer learning technique by re-training these models, and (2) an optimized model similar to EyeDAS, except that it is based on a single expert model which considers the raw images as is (i.e., it computes the image similarity based distance [13] between the raw images directly, without extracting any features as EyeDAS does). In both cases, 220 instances were randomly selected for training; the distribution of 3D and 2D images is approximately 66.7% and 33.3% respectively, and the data augmentation technique described above was applied to avoid an unbalanced training set.…”

Section: Resultsmentioning

confidence: 99%

EyeDAS: Securing Perception of Autonomous Cars Against the Stereoblindness Syndrome

Levy¹,

Nassi²,

Swissa³

et al. 2022

Preprint

View full text Add to dashboard Cite

The ability to detect whether an object is a 2D or 3D object is extremely important in autonomous driving, since a detection error can have life-threatening consequences, endangering the safety of the driver, passengers, pedestrians, and others on the road. Methods proposed to distinguish between 2 and 3D objects (e.g., liveness detection methods) are not suitable for autonomous driving, because they are object dependent or do not consider the constraints associated with autonomous driving (e.g., the need for real-time decision-making while the vehicle is moving). In this paper, we present EyeDAS, a novel few-shot learning-based method aimed at securing an object detector (OD) against the threat posed by the stereoblindness syndrome (i.e., the inability to distinguish between 2D and 3D objects). We evaluate EyeDAS's real-time performance using 2,000 objects extracted from seven YouTube video recordings of street views taken by a dash cam from the driver's seat perspective. When applying EyeDAS to seven state-of-the-art ODs as a countermeasure, EyeDAS was able to reduce the 2D misclassification rate from 71.42-100% to 2.4% with a 3D misclassification rate of 0% (TPR of 1.0). We also show that EyeDAS outperforms the baseline method and achieves an AUC of over 0.999 and a TPR of 1.0 with an FPR of 0.024.

show abstract

“…ResNet tries to solve this problem by learning some residuals instead of features with residual learning. Thus, despite the large number of layers, ResNet-50 is low in complexity and easy to optimize [36][37][38].…”

Section: Obtaining 3d Profile From Laser Camerasmentioning

confidence: 99%

A New Rail Surface Defects Detection Approach Using 3D Laser Cameras Based on ResNet50

Santur¹,

Yilmazer²,

Karaköse³

et al. 2022

View full text Add to dashboard Cite

Rail transportation systems, which are used as one of the most common means of transportation worldwide, should be regularly inspected to prevent accidents that may occur. The rail condition monitoring can be performed in high accuracy and real time using computer vision, deep learning algorithms today. In this study, a new deep learning based approach using 3D laser cameras for rail inspection is presented. In the proposed approach, two 3D laser cameras placed on a real train, seeing the rail line from the left and right surfaces were used. These data consisting of sensitive distance value constitute the input data of the ResNet50 transfer learning model. The training was carried out on Nvidia Cuda supported graphics processing units using ResNet50 Convolutional Neural Network. During the test phase, the operation speed and accuracy rate of the method was measured by repeating the process on real-time rail profiles. The accuracy rate was calculated as 94%. As a result a new approach is presented based on deep learning using 3D laser cameras for rail inspection is presented.

show abstract

A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification

Cited by 244 publications

References 12 publications

A Comparison of Computer-Aided Diagnosis Schemes Optimized Using Radiomics and Deep Transfer Learning Methods

A Comparison of Computer-Aided Diagnosis Schemes Optimized Using Radiomics and Deep Transfer Learning Methods

EyeDAS: Securing Perception of Autonomous Cars Against the Stereoblindness Syndrome

A New Rail Surface Defects Detection Approach Using 3D Laser Cameras Based on ResNet50

Contact Info

Product

Resources

About