Collaborative Learning with Unreliability Adaptation for Semi-Supervised Image Classification

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

3 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number109032
Journal / PublicationPattern Recognition
Volume133
Online published11 Sept 2022
Publication statusPublished - Jan 2023

Abstract

Constructing training goals for unlabeled data is crucial for image classification in the semi-supervised setting. Consistency regularization typically encourages a model to produce consistent predictions with the given training goals, while unreliability adaptation aims to learn the transition probabilities from model predictions to training goals, instead of enforcing their consistency. In this paper, we present a model of Collaborative learning with Unreliability Adaptation (CoUA), in which multiple constituent networks collaboratively learn with each other by adapting their predictions. Toward this end, an additional adaptation module is incorporated into each network to learn a transition probability from its own prediction to that of the paired network. Therefore, the networks can exchange training experience, without being overly sensitive to the unreliability of predictions. To further enhance the collaborative learning, each network is encouraged to produce consistent predictions with the consensus results, while being resistant to the adversarial perturbations against others. Therefore, the networks are able to mutually reinforce each other. We perform extensive experiments on multiple image classification benchmarks to verify the superiority of the co-adaptation based collaborative learning mechanism.

Research Area(s)

  • Collaborative learning, Image classification, Semi-supervised learning, Unreliability adaptation

Citation Format(s)

Collaborative Learning with Unreliability Adaptation for Semi-Supervised Image Classification. / Huo, Xiaoyang; Zeng, Xiangping; Wu, Si et al.
In: Pattern Recognition, Vol. 133, 109032, 01.2023.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review