针对少样本细粒度分类，提出自适应特征分布网络提升准确率。
Task Adaptive Feature Distribution Based Network for Few-shot Fine-grained Target Classification
- 根据任务自适应调整嵌入特征，捕捉细粒度差异
- 采用非对称度量计算查询与支持集间特征分布相似性
- 对比学习策略增强类别区分能力，适合小样本场景
基于度量的少样本细粒度分类因其简洁高效而展现出潜力。然而，现有方法常忽视任务级特殊性，难以精准描述类别并处理无关样本信息。为此，我们提出TAFD-Net：一种任务自适应特征分布网络。该模型包含任务自适应嵌入组件以捕捉任务级细微差别，采用非对称度量计算查询样本与支持类别间特征分布的相似性，并引入对比学习策略提升性能。在三个数据集上的大量实验表明，所提算法优于近期增量学习方法。
原文摘要 · Abstract (English)
Metric-based few-shot fine-grained classification has shown promise due to its simplicity and efficiency. However, existing methods often overlook task-level special cases and struggle with accurate category description and irrelevant sample information. To tackle these, we propose TAFD-Net: a task adaptive feature distribution network. It features a task-adaptive component for embedding to capture task-level nuances, an asymmetric metric for calculating feature distribution similarities between query samples and support categories, and a contrastive measure strategy to boost performance. Extensive experiments have been conducted on three datasets and the experimental results show that our proposed algorithm outperforms recent incremental learning algorithms.
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。