用注意力机制筛选无关特征，提升少样本分类准确率
Slot Attention-based Feature Filtering for Few-Shot Learning
- 引入槽注意力机制，统一过滤无关特征
- 在多个数据集上达到更好分类效果，最高提升3.2%
- 适合处理背景干扰强的少样本场景
无关特征会显著降低少样本学习性能。现有方法依赖查询与支持图像间的语义相似性匹配，但在数据有限时，背景等非相关特征易导致混淆和误分类。为此，我们提出基于槽注意力的特征过滤方法（SAFF），利用槽注意力机制区分并过滤弱特征，从而提升少样本分类性能。SAFF的核心创新在于将槽注意力与图像块嵌入结合，通过单一注意力机制统一建模类感知槽，有效过滤无关特征。我们设计了一个跨支持与查询图像的相似性矩阵，量化过滤后嵌入的相关性以用于分类。实验表明，槽注意力优于其他注意力机制，在捕捉判别性特征的同时减少冗余信息。我们在CIFAR-FS、FC100、miniImageNet和tieredImageNet四个少样本学习基准上进行了充分验证，性能超过多种先进方法。
原文摘要 · Abstract (English)
Irrelevant features can significantly degrade few-shot learn ing performance. This problem is used to match queries and support images based on meaningful similarities despite the limited data. However, in this process, non-relevant fea tures such as background elements can easily lead to confu sion and misclassification. To address this issue, we pro pose Slot Attention-based Feature Filtering for Few-Shot Learning (SAFF) that leverages slot attention mechanisms to discriminate and filter weak features, thereby improving few-shot classification performance. The key innovation of SAFF lies in its integration of slot attention with patch em beddings, unifying class-aware slots into a single attention mechanism to filter irrelevant features effectively. We intro duce a similarity matrix that computes across support and query images to quantify the relevance of filtered embed dings for classification. Through experiments, we demon strate that Slot Attention performs better than other atten tion mechanisms, capturing discriminative features while reducing irrelevant information. We validate our approach through extensive experiments on few-shot learning bench marks: CIFAR-FS, FC100, miniImageNet and tieredIma geNet, outperforming several state-of-the-art methods.
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。