Few-Shot Learning Via Dependency Maximization and Instance Discriminant Analysis

Zejiang Hou, Sun Yuan Kung

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

1 Scopus citations

Abstract

We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches resort to the meta-learning paradigm, where the model accumulates inductive bias through learning many training tasks so as to solve a new unseen few-shot task. In contrast, we propose a simple approach to exploit unlabeled data accompanying the few-shot task for improving few-shot performance. Firstly, we propose a Dependency Maximization method based on the Hilbert-Schmidt norm of the cross-covariance operator, which maximizes the statistical dependency between the embedded feature of those unlabeled data and their label predictions, together with the supervised loss over the support set. We then use the obtained model to infer the pseudo-labels for those unlabeled data. Furthermore, we propose an Instance Discriminant Analysis to evaluate the credibility of each pseudo-labeled example and select the most faithful ones into an augmented support set to retrain the model as in the first step. We iterate the above process until the pseudo-labels for the unlabeled data become stable. Following the standard transductive and semi-supervised FSL setting, our experiments show that the proposed method outperforms previous state-of-The-Art methods on four widely used benchmarks, including mini-ImageNet, tiered-ImageNet, CUB, and CIFARFS.

Original languageEnglish (US)
Title of host publication2021 IEEE 31st International Workshop on Machine Learning for Signal Processing, MLSP 2021
PublisherIEEE Computer Society
ISBN (Electronic)9781728163383
DOIs
StatePublished - 2021
Event31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021 - Gold Coast, Australia
Duration: Oct 25 2021Oct 28 2021

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2021-October
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Conference

Conference31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021
Country/TerritoryAustralia
CityGold Coast
Period10/25/2110/28/21

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Signal Processing

Keywords

  • cross-domain
  • dependency maximization
  • few-shot learning
  • semi-supervised

Fingerprint

Dive into the research topics of 'Few-Shot Learning Via Dependency Maximization and Instance Discriminant Analysis'. Together they form a unique fingerprint.

Cite this