DBDC-SSL: Deep Brownian Distance Covariance With Self-Supervised Learning for Few-Shot Image Classification
Wei Han Liu, Kian Ming Lim, Thian Song Ong, Chin Poo Lee · IEEE Access · 2024
Few-shot image classification remains a persistent challenge due to the intrinsic difficulty faced by visual recognition models in achieving generalization with limited training data. In this paper, we introduce Deep Brownian Distance Covariance with Self-supervised Learning (DBDC-SSL) model, a method that aims to improve few-shot visual recognition models by learning a feature extractor that produces image representations that are more robust. To improve the robustness of the model, Deep Brownian Distance Covariance (DBDC) is employed during the training process to learn better feature embeddings by effectively computing the disparity between product of the marginals and joint characteristic functions of the features, which is often neglected by existing methods that only exploit marginal distributions. To reduce overfitting and improve the generalization of the model, we utilize an auxiliary rotation loss for self-supervised learning (SSL) in the training of the feature extractor. The auxiliary rotation loss is derived from a pretext task, where input images undergo rotation by predefined angles, and the model classifies the rotation angle based on the features it generates. Experimental results demonstrate that the proposed DBDC-SSL outperforms current state-of-the-art methods on four common few-shot image classification benchmark, which are miniImageNet, tieredImageNet, CUB and CIFAR-FS. For 5-way 1-shot and 5-way 5-shot tasks respectively, the proposed DBDC-SSL achieved the accuracy of 68.64±0.43 and 86.02±0.28 on miniImageNet, 73.88±0.48 and 89.03±0.29 on tieredImageNet, 84.67±0.39 and 94.76±0.16 on CUB, and 75.60±0.44 and 88.49±0.31 on CIFAR-FS.