English

Convolutional Ensembling based Few-Shot Defect Detection Technique

Computer Vision and Pattern Recognition 2022-11-24 v3 Artificial Intelligence

Abstract

Over the past few years, there has been a significant improvement in the domain of few-shot learning. This learning paradigm has shown promising results for the challenging problem of anomaly detection, where the general task is to deal with heavy class imbalance. Our paper presents a new approach to few-shot classification, where we employ the knowledge-base of multiple pre-trained convolutional models that act as the backbone for our proposed few-shot framework. Our framework uses a novel ensembling technique for boosting the accuracy while drastically decreasing the total parameter count, thus paving the way for real-time implementation. We perform an extensive hyperparameter search using a power-line defect detection dataset and obtain an accuracy of 92.30% for the 5-way 5-shot task. Without further tuning, we evaluate our model on competing standards with the existing state-of-the-art methods and outperform them.

Keywords

Cite

@article{arxiv.2208.03288,
  title  = {Convolutional Ensembling based Few-Shot Defect Detection Technique},
  author = {Soumyajit Karmakar and Abeer Banerjee and Prashant Sadashiv Gidde and Sumeet Saurav and Sanjay Singh},
  journal= {arXiv preprint arXiv:2208.03288},
  year   = {2022}
}

Comments

7 pages, 7 images

R2 v1 2026-06-25T01:31:15.836Z