Few-Shot Partial-Label Learning

by   Yunfeng Zhao, et al.

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.


page 1

page 2

page 3

page 4


Revisiting Metric Learning for Few-Shot Image Classification

The goal of few-shot learning is to recognize new visual concepts with j...

Few-shot Learning with LSSVM Base Learner and Transductive Modules

The performance of meta-learning approaches for few-shot learning genera...

Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation

The field of few-shot learning has been laboriously explored in the supe...

OTS: A One-shot Learning Approach for Text Spotting in Historical Manuscripts

Historical manuscript processing poses challenges like limited annotated...

Additive Angular Margin for Few Shot Learning to Classify Clinical Endoscopy Images

Endoscopy is a widely used imaging modality to diagnose and treat diseas...

LFD-ProtoNet: Prototypical Network Based on Local Fisher Discriminant Analysis for Few-shot Learning

The prototypical network (ProtoNet) is a few-shot learning framework tha...

Adaptive Posterior Learning: few-shot learning with a surprise-based memory module

The ability to generalize quickly from few observations is crucial for i...

Please sign up or login with your details

Forgot password? Click here to reset