Few-Shot Partial-Label Learning

TL;DR

This paper introduces FsPLL, a novel method for few-shot partial-label learning that effectively classifies new tasks with limited samples by adaptive metric learning and prototype rectification.

Contribution

FsPLL is the first approach to address partial-label learning in a few-shot setting, combining adaptive metric learning with prototype rectification for improved performance.

Findings

FsPLL outperforms state-of-the-art methods on Omniglot and miniImageNet datasets.

It requires fewer samples to adapt to new tasks effectively.

FsPLL demonstrates robustness in few-shot partial-label classification scenarios.

Abstract

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of existing PLL solutions is that there are sufficient partial-label (PL) samples for training. However, it is more common than not to have just few PL samples at hand when dealing with new tasks. Furthermore, existing few-shot learning algorithms assume precise labels of the support set; as such, irrelevant labels may seriously mislead the meta-learner and thus lead to a compromised performance. How to enable PLL under a few-shot learning setting is an important problem, but not yet well studied. In this paper, we introduce an approach called FsPLL (Few-shot PLL). FsPLL first performs adaptive distance metric learning by an embedding network and rectifying prototypes on the tasks previously encountered. Next, it calculates the prototype of each class of a new task in the embedding network. An unseen example can then be classified via its distance to each prototype. Experimental results on widely-used few-shot datasets (Omniglot and miniImageNet) demonstrate that our FsPLL can achieve a superior performance than the state-of-the-art methods across different settings, and it needs fewer samples for quickly adapting to new tasks.