Calibrating CNNs for Few-Shot Meta Learning

Peng Yang, Shaogang Ren, Yang Zhao, Ping Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Although few-shot meta learning has been extensively studied in machine learning community, the fast adaptation towards new tasks remains a challenge in the few-shot learning scenario. The neuroscience research reveals that the capability of evolving neural network formulation is essential for task adaptation, which has been broadly studied in recent meta-learning researches. In this paper, we present a novel forward-backward meta-learning framework (FBM) to facilitate the model generalization in few-shot learning from a new perspective, i.e., neuron calibration. In particular, FBM models the neurons in deep neural network-based model as calibrated units under a general formulation, where neuron calibration could empower fast adaptation capability to the neural network-based models through influencing both their forward inference path and backward propagation path. The proposed calibration scheme is lightweight and applicable to various feed-forward neural network architectures. Extensive empirical experiments on the challenging few-shot learning benchmarks validate that our approach training with neuron calibration achieves a promising performance, which demonstrates that neuron calibration plays a vital role in improving the few-shot learning performance.

Original languageAmerican English
Title of host publicationProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages408-417
Number of pages10
ISBN (Electronic)9781665409155
DOIs
StatePublished - 2022
Event22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022 - Waikoloa, United States
Duration: Jan 4 2022Jan 8 2022

Publication series

NameProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022

Conference

Conference22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
Country/TerritoryUnited States
CityWaikoloa
Period1/4/221/8/22

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Keywords

  • Few-shot
  • Learning and Optimization
  • Semi- and Un- supervised Learning Deep Learning
  • Statistical Methods
  • Transfer

Fingerprint

Dive into the research topics of 'Calibrating CNNs for Few-Shot Meta Learning'. Together they form a unique fingerprint.

Cite this