SSGAN: A Semantic Similarity-Based GAN for Small-Sample Image Augmentation

Article Properties
Abstract
Cite
Ma, Congcong, et al. “SSGAN: A Semantic Similarity-Based GAN for Small-Sample Image Augmentation”. Neural Processing Letters, vol. 56, no. 3, 2024, https://doi.org/10.1007/s11063-024-11498-z.
Ma, C., Mi, J., Gao, W., & Tao, S. (2024). SSGAN: A Semantic Similarity-Based GAN for Small-Sample Image Augmentation. Neural Processing Letters, 56(3). https://doi.org/10.1007/s11063-024-11498-z
Ma C, Mi J, Gao W, Tao S. SSGAN: A Semantic Similarity-Based GAN for Small-Sample Image Augmentation. Neural Processing Letters. 2024;56(3).
Journal Categories
Science
Mathematics
Instruments and machines
Electronic computers
Computer science
Description

Need more data for your AI models? This paper introduces SSGAN, a novel semantic similarity-based Generative Adversarial Network (GAN) designed for image augmentation in small-sample scenarios. Image sample augmentation refers to strategies for increasing sample size by modifying current data or synthesizing new data based on existing data. SSGAN aims to address the limitations of traditional GANs when applied to datasets with limited samples. The method incorporates a shallow pyramid-structured GAN backbone to enhance feature extraction and a feature selection module based on high-dimensional semantics to optimize the loss function. Evaluated on the "Flower" and "Animal" datasets, SSGAN outperforms classical GAN methods in FID and IS metrics, showing improvements of 18.6 and 1.4, respectively. The dataset augmented by SSGAN significantly enhances the performance of the classifier, achieving a 2.2% accuracy improvement compared to the best-known method. SSGAN demonstrates excellent generalization and robustness, providing a valuable tool for improving the performance of downstream learning tasks in small-sample image recognition challenges.

Appearing in Neural Processing Letters, this paper fits within the journal’s scope of publishing research on neural networks and related areas of computer science. The introduction of SSGAN, a semantic similarity-based GAN, directly addresses the journal’s focus on advancing image augmentation techniques, a key area in neural processing and machine learning.

Refrences
Refrences Analysis
The category Science: Mathematics: Instruments and machines: Electronic computers. Computer science 4 is the most frequently represented among the references in this article. It primarily includes studies from Expert Systems with Applications The chart below illustrates the number of referenced publications per year.
Refrences used by this article by year