SVMnet: Non-Parametric Image Classification Based on Convolutional Ensembles of Support Vector Machines for Small Training Sets

Goddard, Hunter; Shamir, Lior

doi:10.1109/access.2022.3154405

Cited by 4 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Limited Labeled Datasets: The small number of publicly available, high-quality labeled datasets and a reliance on single-source datasets contribute to the issue of overfitting in some models. To address this, various data augmentation techniques have been proposed, including elastic deformation and the utilization of advanced models such as GANs, diffusion models, variational autoencoders, and SVMNet [44,164]. Moreover, the application of few-shot learning techniques, as demonstrated in the Hesse et al study [117], can be instrumental in enhancing the performance of models with limited data.…”

Section: Discussionmentioning

confidence: 99%

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

Yousefpour Shahrivar,

Karami,

Karami

2023

Biomimetics

View full text Add to dashboard Cite

Fetal development is a critical phase in prenatal care, demanding the timely identification of anomalies in ultrasound images to safeguard the well-being of both the unborn child and the mother. Medical imaging has played a pivotal role in detecting fetal abnormalities and malformations. However, despite significant advances in ultrasound technology, the accurate identification of irregularities in prenatal images continues to pose considerable challenges, often necessitating substantial time and expertise from medical professionals. In this review, we go through recent developments in machine learning (ML) methods applied to fetal ultrasound images. Specifically, we focus on a range of ML algorithms employed in the context of fetal ultrasound, encompassing tasks such as image classification, object recognition, and segmentation. We highlight how these innovative approaches can enhance ultrasound-based fetal anomaly detection and provide insights for future research and clinical implementations. Furthermore, we emphasize the need for further research in this domain where future investigations can contribute to more effective ultrasound-based fetal anomaly detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

Yousefpour Shahrivar,

Karami,

Karami

2023

Biomimetics

View full text Add to dashboard Cite

show abstract

“…In sum, these modifications aid in honing task-specific adaptation, resulting in faster responsiveness and more widespread generalization. Integrating data parallelism with Nesterov's momentum can significantly improve the speed and accuracy of model convergence [8,9]. The former splits data across multiple processors and uses multiple model instances to efficiently estimate gradients [10].…”

Section: Introductionmentioning

confidence: 99%

LaANIL: ANIL with Look-Ahead Meta-Optimization and Data Parallelism

Tammisetti,

Bierzynski,

Stettinger

et al. 2024

Electronics

View full text Add to dashboard Cite

Meta-few-shot learning algorithms, such as Model-Agnostic Meta-Learning (MAML) and Almost No Inner Loop (ANIL), enable machines to learn complex tasks quickly with limited data and based on previous experience. By maintaining the inner loop head of the neural network, ANIL leads to simpler computations and reduces the complexity of MAML. Despite its benefits, ANIL suffers from issues like accuracy variance, slow initial learning, and overfitting, hardening its adaptation and generalization. This work proposes “Look-Ahead ANIL” (LaANIL), an enhancement to ANIL for better learning. LaANIL reorganizes ANIL’s internal architecture, integrating parallel computing techniques (to process multiple training examples simultaneously across computing units) and incorporating Nesterov momentum (which accelerates convergence by adjusting the learning rate based on past gradient information and extracting informative features for look-ahead gradient computation). These additional features make our model more state-of-the-art capable and better edge-compatible and thus improve few-short learning by enabling models to quickly adapt to new information and tasks. LaANIL’s effectiveness is validated on established meta-few-shot learning datasets, including FC100, CIFAR-FS, Mini-ImageNet, CUBirds-200-2011, and Tiered-ImageNet. The proposed model achieved an increased validation accuracy by 7 ± 0.7% and a variance reduction by 44 ± 4% in two-way two-shot classification as well as increased validation by 5 ± 0.4% and a variance reduction by 18 ± 2% in five-way five-shot classification on the FC100 dataset and similarly performed well on other datasets.

show abstract

“…There are many theoretical achievements in support vector machine algorithm and rail road fault diagnosis. For example, some scholars said that introducing incremental learning into support vector machine integration can make full use of the support vector set obtained from historical training results [1][2]. Some scholars also believe that it is of great significance to improve the intelligent level of railway signal maintenance by using genetic algorithm and particle swarm optimization algorithm to optimize the parameters and then realize the judgment of fault types [3][4].…”

Section: Introductionmentioning

confidence: 99%

Track Circuit Fault Diagnosis Method Based on Support Vector Machine Algorithm

2021

View full text Add to dashboard Cite

Rail transit is an important mode of transportation in urban construction. In recent years, China has put forward higher requirements for subway, light rail and other public transport tools. In order to improve the stability of rail transit, the support vector machine algorithm is used to improve the fault diagnosis ability to facilitate people. This paper mainly uses experimental method and comparison method to support vector machine, GA algorithm and other algorithms in track road diagnosis. The experimental results show that the recognition rate of some faults can reach 100%, which shows that the design scheme in this paper has some reference significance.

show abstract

SVMnet: Non-Parametric Image Classification Based on Convolutional Ensembles of Support Vector Machines for Small Training Sets

Cited by 4 publications

References 39 publications

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

LaANIL: ANIL with Look-Ahead Meta-Optimization and Data Parallelism

Track Circuit Fault Diagnosis Method Based on Support Vector Machine Algorithm

Contact Info

Product

Resources

About