用自监督预训练提升ResNet-101在小样本图像分类中的表现。
Self-Supervised Learning in Deep Networks: A Pathway to Robust Few-Shot Classification
- 先在无标签数据上自监督预训练，再微调到小样本数据集。
- 在Mini-ImageNet上达到95.12%准确率，显著优于基准模型。
- 适合资源有限但需快速适应新类别的图像识别任务。
本研究通过将自监督学习与深度网络ResNet-101结合，优化小样本图像分类任务中的特征提取与分类性能。训练过程首先在大规模无标签数据上进行自监督预训练，使模型学习通用特征表示；随后在小样本数据集Mini-ImageNet上微调，以提升模型在有限数据下的准确率与泛化能力。实验结果表明，相较于传统卷积神经网络、ResNet-50和DenseNet等模型，该方法在分类准确率（ACC）和F1得分上均达到约95.12%的优异表现，验证了自监督学习在小样本分类中的有效性。该方法为小样本图像分类领域提供了高效可靠的解决方案。
原文摘要 · Abstract (English)
This study aims to optimize the few-shot image classification task and improve the model's feature extraction and classification performance by combining self-supervised learning with the deep network model ResNet-101. During the training process, we first pre-train the model with self-supervision to enable it to learn common feature expressions on a large amount of unlabeled data; then fine-tune it on the few-shot dataset Mini-ImageNet to improve the model's accuracy and generalization ability under limited data. The experimental results show that compared with traditional convolutional neural networks, ResNet-50, DenseNet, and other models, our method has achieved excellent performance of about 95.12% in classification accuracy (ACC) and F1 score, verifying the effectiveness of self-supervised learning in few-shot classification. This method provides an efficient and reliable solution for the field of few-shot image classification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。