Few-shot learning (FSL) based on manifold regularization aims to improve the
recognition capacity of novel objects with limited training samples by mixing
two samples from different categories with a blending factor. However, this
mixing operation weakens the feature representation due to the linear
interpolation and the overlooking of the importance of specific channels. To
solve these issues, this paper proposes attentive feature regularization (AFR)
which aims to improve the feature representativeness and discriminability. In
our approach, we first calculate the relations between different categories of
semantic labels to pick out the related features used for regularization. Then,
we design two attention-based calculations at both the instance and channel
levels. These calculations enable the regularization procedure to focus on two
crucial aspects: the feature complementarity through adaptive interpolation in
related categories and the emphasis on specific feature channels. Finally, we
combine these regularization strategies to significantly improve the classifier
performance. Empirical studies on several popular FSL benchmarks demonstrate
the effectiveness of AFR, which improves the recognition accuracy of novel
categories without the need to retrain any feature extractor, especially in the
1-shot setting. Furthermore, the proposed AFR can seamlessly integrate into
other FSL methods to improve classification performance.

基于多样性正则化的少样本学习旨在通过混合来自不同类别的两个样本及其融合因子的方法，提高对有限训练样本的新颖对象的识别能力。然而，这种混合操作通过线性插值和忽视特定通道的重要性削弱了特征表示。为了解决这些问题，本文提出了一种注意力特征正则化（AFR）的方法，旨在提高特征的代表性和可辨识性。在我们的方法中，我们首先计算不同语义标签类别之间的关系，以挑选用于正则化的相关特征。然后，我们在实例和通道级别设计了两个基于注意力的计算方法。这些计算使正则化过程能够关注两个关键方面：通过相关类别中的自适应插值来提高特征的互补性，以及强调特定的特征通道。最后，我们结合这些正则化策略显著提高了分类器的性能。对几个流行的少样本学习基准进行的实证研究证明了 AFR 的有效性，它提高了新颖类别的识别准确性，而无需重新训练任何特征提取器，特别是在 1-shot 设置中。此外，所提出的 AFR 可以无缝集成到其他少样本学习方法中，以提高分类性能。