Boosting Meta-Training with Base Class Information for Few-Shot Learning Article Swipe

MAKE IMPACT

Weihao Jiang , Guodong Liu , Di He , Kun He · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2403.03472

Few-shot learning, a challenging task in machine learning, aims to learn a classifier adaptable to recognize new, unseen classes with limited labeled examples. Meta-learning has emerged as a prominent framework for few-shot learning. Its training framework is originally a task-level learning method, such as Model-Agnostic Meta-Learning (MAML) and Prototypical Networks. And a recently proposed training paradigm called Meta-Baseline, which consists of sequential pre-training and meta-training stages, gains state-of-the-art performance. However, as a non-end-to-end training method, indicating the meta-training stage can only begin after the completion of pre-training, Meta-Baseline suffers from higher training cost and suboptimal performance due to the inherent conflicts of the two training stages. To address these limitations, we propose an end-to-end training paradigm consisting of two alternative loops. In the outer loop, we calculate cross entropy loss on the entire training set while updating only the final linear layer. In the inner loop, we employ the original meta-learning training mode to calculate the loss and incorporate gradients from the outer loss to guide the parameter updates. This training paradigm not only converges quickly but also outperforms existing baselines, indicating that information from the overall training set and the meta-learning training paradigm could mutually reinforce one another. Moreover, being model-agnostic, our framework achieves significant performance gains, surpassing the baseline systems by approximate 1%.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2403.03472

PDF

https://arxiv.org/pdf/2403.03472

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4392575728

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4392575728

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2403.03472

Digital Object Identifier

Title

Boosting Meta-Training with Base Class Information for Few-Shot Learning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2024

Year of publication

Publication date

2024-03-06

Full publication date if available

Authors

Weihao Jiang, Guodong Liu, Di He, Kun He

List of authors in order

Landing page

https://arxiv.org/abs/2403.03472

Publisher landing page

PDF URL

https://arxiv.org/pdf/2403.03472

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2403.03472

Direct OA link when available

Concepts

Boosting (machine learning), Shot (pellet), Computer science, Class (philosophy), Training (meteorology), Artificial intelligence, Base (topology), Machine learning, Training set, One shot, Engineering, Mathematics, Geography, Materials science, Mathematical analysis, Metallurgy, Meteorology, Mechanical engineering

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload