We conduct a systematic comparison of methods in a variety of domains, varying thenumber oflabeled instances available inthetargetdomain (k), as well as the number of target-domain classes.

In this experiment, we modify ProtoNet slightly to fit regression problem. In detail, we try to meta-learn an embedding functionφ: R R100, with assistance of which the similarity-based regressionmodelg(;{φ(xi)|(xi,yi) S})workswellacrossalltasks.

It is often realized through optimizing a metamodel withtheevaluation lossoftask-specific solvers.

Sc The subset of examples inS that belong to classc: Sc = {(xi,yi)|(xi,yi) S,yi =c} f The base model.

Multiple versions of this dataset exist in the literature; we use the version by Ravi and Larochelle [43]. The original version of the dataset contains43images that are also present in ImageNet. We remove these duplicates to avoid overestimating the transfer capability during evaluation. VGGFlowers: Originally introduced by Nilsback and Zisserman[38], VGGFlowers consists of 102 flower categories with each category containing between40 and 258 images. A.3 Trainingalgorithms For the metric-based family, we use ProtoNet with Euclidean [53] and scaled negative cosine similarity measures [20].

In RPMs, the relational concepts come from a small set of five relations [17].

Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical. While extensive research has been conducted in the image domain, few-shot learning in audio classification remains relatively underexplored. In this work, we investigate the effect of integrating supervised contrastive loss into prototypical few shot training for audio classification. In detail, we demonstrate that angular loss further improves the performance compared to the standard contrastive loss. Our method leverages SpecAugment followed by a self-attention mechanism to encapsulate diverse information of augmented input versions into one unified embedding. We evaluate our approach on MetaAudio, a benchmark including five datasets with predefined splits, standardized preprocessing, and a comprehensive set of few-shot learning models for comparison. The proposed approach achieves state-of-the-art performance in a 5-way, 5-shot setting.