Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

TL;DR

This paper introduces FEAT, a novel few-shot learning method that adapts embeddings using set-to-set functions, particularly Transformers, to produce task-specific, discriminative features, achieving state-of-the-art results across multiple benchmarks.

Contribution

The paper proposes a new embedding adaptation approach using set-to-set functions, especially Transformers, for improved few-shot learning performance.

Findings

Transformers are most effective as set-to-set functions for embedding adaptation.

FEAT achieves consistent improvements over baseline and previous methods.

State-of-the-art results on standard and extended few-shot learning benchmarks.

Abstract

Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. We empirically investigated various instantiations of such set-to-set functions and observed the Transformer is most effective -- as it naturally satisfies key properties of our desired model. We denote this model as FEAT (few-shot embedding adaptation w/ Transformer) and validate it on both the standard few-shot classification benchmark and four extended few-shot learning settings with essential use cases, i.e., cross-domain, transductive, generalized few-shot learning, and low-shot learning. It archived consistent improvements over baseline models as well as previous methods and established the new state-of-the-art results on two benchmarks.