arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.01427cs.CVcs.AI
收藏

用于少样本图像分类的连体 Transformer 网络

Siamese Transformer Networks for Few-shot Image Classification

Weihao Jiang, Shuoxi Zhang, Kun He

AI总结:

本文提出 Siamese Transformer Network,用双分支 ViT-Small 分别提取全局与局部特征,并融合欧氏距离和 KL 散度进行少样本图像分类,在四个基准上超越现有方法。

摘要:

人类在视觉分类任务中表现出非凡的熟练程度,能够用极少的示例准确识别和分类新图像。这种能力归因于他们能够关注细节,并识别先前见过的图像与新图像之间的共同特征。相比之下,现有的少样本图像分类方法往往强调全局特征或局部特征之一,很少有研究考虑将两者结合。为解决这一局限,我们提出了一种基于 Siamese Transformer Network(STN,连体 Transformer 网络)的新颖方法。该方法采用两个并行分支网络,利用预训练的 Vision Transformer(ViT)架构分别提取全局特征和局部特征。具体而言,我们实现了 ViT-Small 网络架构,并使用通过自监督学习获得的预训练模型参数初始化分支网络。我们对全局特征应用欧几里得距离度量,对局部特征应用 Kullback-Leibler(KL)散度度量。为整合这两种度量,我们首先采用 L2 归一化,然后对归一化结果加权,以获得最终相似度分数。该策略利用了全局特征和局部特征的优势,同时确保二者的互补收益。在训练阶段,我们采用元学习方法对整个网络进行微调。我们的策略有效挖掘了全局特征和局部特征在少样本图像分类中的潜力,避免了对复杂特征适配模块的需求,并增强了模型的泛化能力。大量实验表明,我们的框架简单而有效,在四个流行的少样本分类基准上的 5-shot 和 1-shot 场景中均取得了优于最先进基线的性能。

英文摘要:

Humans exhibit remarkable proficiency in visual classification tasks, accurately recognizing and classifying new images with minimal examples. This ability is attributed to their capacity to focus on details and identify common features between previously seen and new images. In contrast, existing few-shot image classification methods often emphasize either global features or local features, with few studies considering the integration of both. To address this limitation, we propose a novel approach based on the Siamese Transformer Network (STN). Our method employs two parallel branch networks utilizing the pre-trained Vision Transformer (ViT) architecture to extract global and local features, respectively. Specifically, we implement the ViT-Small network architecture and initialize the branch networks with pre-trained model parameters obtained through self-supervised learning. We apply the Euclidean distance measure to the global features and the Kullback-Leibler (KL) divergence measure to the local features. To integrate the two metrics, we first employ L2 normalization and then weight the normalized results to obtain the final similarity score. This strategy leverages the advantages of both global and local features while ensuring their complementary benefits. During the training phase, we adopt a meta-learning approach to fine-tune the entire network. Our strategy effectively harnesses the potential of global and local features in few-shot image classification, circumventing the need for complex feature adaptation modules and enhancing the model's generalization ability. Extensive experiments demonstrate that our framework is simple yet effective, achieving superior performance compared to state-of-the-art baselines on four popular few-shot classification benchmarks in both 5-shot and 1-shot scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑