Augmenting Few-Shot Learning With Supervised Contrastive Learning

Lee, Taemin; Yoo, Sungjoo

doi:10.1109/access.2021.3074525

Cited by 17 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After determining the mapping function, it may be used to analyze added information for which the output value is not known [12]. If there are enough training examples and a suitable learning method is used, the algorithm will be able of generalization successfully, or give correct results for inputs that are similar but not identical to those in the dataset.…”

Section: The Methods Of Supervised Learningmentioning

confidence: 99%

Supervised Learning Methods and Applications in Medical Research

Ming

Yuan

2022

JCNS

View full text Add to dashboard Cite

Machine Learning (ML) and Artificial Intelligence (AI) methods are transforming many commercial and academic areas, including feature extraction, autonomous driving, computational linguistics, and voice recognition. These new technologies are now having a significant effect in radiography, forensics, and many other areas where the accessibility of automated systems may improve the precision and repeatability of essential job performance. In this systematic review, we begin by providing a short overview of the different methods that are currently being developed, with a particular emphasis on those utilized in biomedical studies.

show abstract

Section: The Methods Of Supervised Learningmentioning

confidence: 99%

Supervised Learning Methods and Applications in Medical Research

Ming

Yuan

2022

JCNS

View full text Add to dashboard Cite

show abstract

“…Ma [17] fuses advanced feature detail enhancement and multi-scale features for contextual semantic edge detection. Ju [18] proposes the attention mechanism for multi-scale target detection by adaptively learning the importance and relevance ideas of features at different scales with the Lee [19] computed enhanced feature extraction networks by contrast learning. To cope with scale variations.…”

Section: Related Workmentioning

confidence: 99%

IFE-net: improved feature enhancement network for weak feature target recognition in autonomous underwater vehicles

Cai,

Zhang,

et al. 2024

Robotica

View full text Add to dashboard Cite

The recognizing underwater targets is a crucial component of autonomous underwater vehicle patrols and detection efforts. In the process of visual image recognition in real underwater environment, the spatial and semantic features of the target often appear to different degrees of loss, and the scarcity of specific types of underwater samples leads to unbalanced data on categories. This kind of problem makes the target features appear weak and seriously affects the accuracy of underwater target recognition. Traditional deep learning methods based on data and feature enhancement cannot achieve ideal recognition effect. Based on the above difficulties, this paper proposes an improved feature enhancement network for weak feature target recognition. Firstly, a multi-scale spatial and semantic feature enhancement module is constructed to extract the feature information of the extraction target accurately. Secondly, this paper solves the influence of target feature distortion on classification through multi-scale feature comparison of positive and negative samples. Finally, the Rank & Sort Loss function was used to train the depth target detection to solve the problem of recognition accuracy under highly unbalanced sample data. Experimental results show that the recognition accuracy of the proposed method is 2.28% and 3.84% higher than that of the existing algorithms in the recognition of underwater fuzzy and distorted target images, which demonstrates the effectiveness and superiority of the proposed method.

show abstract

“…Meta-learning improves deep learning models by enabling them to learn from a variety of tasks, enhancing their ability to quickly adapt to new and unseen tasks with minimal additional data. In contrast, conventional deep learning has many limitations, including the inability to learn new tasks as quickly as humans do when drawing on prior experience, and many classifiers require massive amounts of training data [15]. Furthermore, deep learning algorithm performance depends heavily on labeled data with predefined attributes, which sometimes restricts generalization.…”

Section: Meta-learningmentioning

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

Augmenting Few-Shot Learning With Supervised Contrastive Learning

Cited by 17 publications

References 26 publications

Supervised Learning Methods and Applications in Medical Research

Supervised Learning Methods and Applications in Medical Research

IFE-net: improved feature enhancement network for weak feature target recognition in autonomous underwater vehicles

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

Contact Info

Product

Resources

About