• Home
  • Search
  • Classification Using Transfer Learning and SWIN-MAE Model on Small-Scale Datasets
  • https://doi.org/10.1109/iccect64621.2025.11339758Copy DOI Icon

Classification Using Transfer Learning and SWIN-MAE Model on Small-Scale Datasets

  • Apr 25, 2025
  • Honglin Hui +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

In the field of pattern recognition, a specific classification challenge arises from a small dataset that is critical for distinguishing between different categories. The development of efficient automated classification algorithms is essential to accurately identify and categorize instances within this dataset at an early stage, which is analogous to the importance of early diagnosis and treatment in other domains. This research aims to enhance the precision and efficiency of classification tasks, emphasizing the value of timely and accurate categorization. To address the challenges of high annotation costs, limited model generalization, and data privacy in the context of a specific classification task, this paper introduces a method based on a small-scale dataset and transfer learning. The approach employs the SWIN-MAE model for pre-training and integrates the SWIN-Transformer block for feature extraction, thereby significantly enhancing the model's classification capabilities. The experimental results indicate that this method achieves an accuracy of 98.02%, a sensitivity of 96.25%, and a specificity of 95.62% on the classification task at hand, surpassing other mainstream models and showcasing high efficiency and precision.

Similar Papers
  • Components

Table 8: Performance of various mainstream models in classification.

  • Dec 07, 2021
  • Research Article
  • Citations2

A hybrid approach based on transfer and ensemble learning for improving performances of deep learning models on small datasets

  • Nov 30, 2021
  • TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES
  • Tunç Gültekin +1
  • Research Article
  • Citations9

Comparative analysis of deep convolution neural network models on small scale datasets

  • Nov 13, 2022
  • Optik
  • C.R Edwin Selva Rex +2
  • Research Article
  • Citations3

Multilayer meta-matching: translating phenotypic prediction models from multiple datasets to small data

  • Dec 07, 2023
  • bioRxiv
  • Pansheng Chen +13
  • Research Article

Machine learning model predicted thermodynamic stability of rare earth compounds

  • Jan 01, 2025
  • Acta Physica Sinica
  • Chenglong Qin +2
  • Research Article
  • Citations2

Multi-label classification of chest X-ray images with pre-trained vision Transformer model

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Xing Suxia +4
  • Book Chapter
  • Citations2

Effect of Small Dataset Quality on Deep Neural Network Performance for Lyme Disease Classification

  • Sep 30, 2022
  • Illia Oholtsov +2
  • Research Article
  • Citations13

Data-Efficient Classification of Radio Galaxies

  • Oct 30, 2021
  • Monthly Notices of the Royal Astronomical Society
  • Ashwin Samudre +3
  • Research Article

FRACTURE DETECTION IN WRIST TRAUMA RADIOGRAPH: OPTIMIZING ALGORITHM PERFORMANCE USING TRANSFER LEARNING

  • Nov 14, 2024
  • Orthopaedic Proceedings
  • F Birkholtz +3
  • Conference Article
  • Citations2

A Feature Extraction Intelligent Music Genre Classification Method Based on Deep Learning Technology

  • Apr 26, 2024
  • Shuqi Si
  • PDF
  • Research Article
  • Citations3

Transferability prediction among classification and regression tasks using optimal transport

  • Aug 21, 2023
  • Multimedia Tools and Applications
  • Tomoyuki Hatakeyama +2
  • PDF
  • Research Article
  • Citations39

Transfer Learning: Making Retrosynthetic Predictions Based on a Small Chemical Reaction Dataset Scale to a New Level

  • May 19, 2020
  • Molecules
  • Renren Bai +5
  • Conference Article
  • Citations1

Deep Learning Techniques for Voice Disorder Detection: A Transfer Learning and Data Augmentation Approach

  • Jul 24, 2025
  • Smitha Rai +1
  • Research Article
  • Citations63

Domain- and task-specific transfer learning for medical segmentation tasks

  • Nov 23, 2021
  • Computer Methods and Programs in Biomedicine
  • Riaan Zoetmulder +3
  • Research Article
  • Citations99

Improving Alzheimer's stage categorization with Convolutional Neural Network using transfer learning and different magnetic resonance imaging modalities

  • Dec 01, 2020
  • Heliyon
  • Karim Aderghal +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.