NegCosIC: Negative Cosine Similarity-Invariance- Covariance Regularization for Few-Shot Learning

Wei Han Liu, Kian Ming Lim*, Thian Song Ong, Chin Poo Lee

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Few-shot learning continues to pose a challenge as it is inherently difficult for visual recognition models to generalize with limited labeled examples. When the training data is limited, the process of training and fine-tuning the model will be unstable and inefficient due to overfitting. In this paper, we introduce NegCosIC: Negative Cosine Similarity-Invariance-Covariance Regularization, a method that aims to improve the mean accuracy from the perspective of stabilizing the fine-tuning process and regularizing variance. NegCosIC incorporates a negative simple cosine similarity loss to stabilize the parameters of the feature extractor during fine-tuning. In addition, NegCosIC integrates invariance loss and covariance loss to regularize the embeddings in order to reduce overfitting. Experimental results demonstrate that NegCosIC is able to bring substantial improvements over the current state-of-the-art methods. An in-depth worse case analysis is also conducted and shows that NegCosIC is able to outperform state-of-the-art methods on worst case accuracy. The proposed NegCosIC achieved 2.15% and 2.13% higher accuracy on miniImageNet 1-shot and 5-shot tasks, 3.22% and 2.67% higher accuracy on CUB 1-shot and 5-shot tasks, and 2.13% and 7.74% higher accuracy on CIFAR-FS 1-shot and 5-shot tasks in terms of worst-case accuracies.

Original languageEnglish
Pages (from-to)52867-52877
Number of pages11
JournalIEEE Access
Volume12
DOIs
Publication statusPublished - 2024
Externally publishedYes

Keywords

  • covariance
  • Few-shot learning
  • invariance
  • negative cosine similarity
  • regularization

Fingerprint

Dive into the research topics of 'NegCosIC: Negative Cosine Similarity-Invariance- Covariance Regularization for Few-Shot Learning'. Together they form a unique fingerprint.

Cite this