通过可变特征融合提升少样本视觉学习性能
VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning
- 用小型变分自编码器融合多尺度特征图，动态调节信息流
- 在CIFAR-100和Mini-ImageNet上优于主流基线模型
- 对高分辨率特征敏感，训练策略是性能关键
本文提出VDLF-Net，将一个紧凑的变分自编码器（VAE）接入多尺度卷积神经网络主干。潜在向量与软门控机制支持主干特征图，经门控后的ℓ₂归一化嵌入用于监督分类或时序少样本预测。在标准CIFAR-100和Mini-ImageNet协议下，VDLF-Net表现优于增强版ResNet-50、VGG-16、原型网络和匹配网络。大量消融实验表明，移除细粒度分辨率层级对性能影响最大；同时，在选定α值下的KL散度与重构损失对性能影响较小，说明性能提升主要源于完整架构与训练策略。
原文摘要 · Abstract (English)
This paper introduces VDLF-Net, which attaches a compact VAE to a multi-scale CNN backbone. Latent vectors and softmax-gate support the backbone feature maps, while $\ell_2$-normalized embeddings from the gated maps contribute toward supervised classification or episodic few-shot prediction. Under standard CIFAR-100 and Mini-ImageNet protocols, VDLF-Net demonstrates an improved performance over ResNet-50 Enhanced, VGG-16, Prototypical Networks, and Matching Networks. Extensive ablations show that removing the fine-resolution scale has the greatest impact on VDLF-Net's performance. At the same time, KL and reconstruction at the chosen $α$ pose a minor performance reduction, demonstrating that performance gains over classical episodic baselines mainly originate from the full VDLF-Net architecture and training strategy.
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。