Few-shot contrastive learning for image classification and its application to insulator identification

Abstract

This paper presents a novel discriminative Few-shot learning architecture based on batch compact loss. Currently, Convolutional Neural Network (CNN) has achieved reasonably good performance in image recognition. Most existing CNN methods facilitate classifiers to learn discriminating patterns to identify existing categories trained with large samples. However, learning to recognize novel categories from a few examples is a challenging task. To address this, we propose the Residual Compact Network to train a deep neural network to learn hierarchical nonlinear transformations to project image pairs into the same latent feature space, under which the distance of each positive pair is reduced. To better use the commonality of class-level features for category recognition, we develop a batch compact loss to form robust feature representations relevant to a category. The proposed methods are evaluated on several datasets. Experimental evaluations show that our proposed method achieves acceptable results in Few-shot learning.

Deep Residual Learning for Image Recognition: A Survey

“…The author in [5] ends their study by concluding that deep residual learning for image recognition is a promising direction in image recognition. They note that deep residual learning for image recognition is computationally efficient, more accurate and suitable for sparse data representations.…”

A residual dense comprehensively regulated convolutional neural network to identify spectral information for egg quality traceability

“…Gao et al 34 proposed a multi-scale residual network for hyperspectral image classification. Li et al 35 designed a residual compact network to train a deep neural network for insulator recognition. These methods apply residual connections, avoiding feature degradation by guiding deep features with original features through identity transformation.…”

“…Ahuja 13 and Oyewola 33 et al applied only one residual connection at the beginning to end (ResBTE) of their designed modules. Gao 34 and Li 35 et al connected multiple residual connections in series (ResCMS). Nevertheless, they suffer from the drawback of not fully utilizing the information of each convolution layer.…”