Collaborative Learning with Unreliability Adaptation for Semi-Supervised Image Classification

doi:10.1016/j.patcog.2022.109032

Collaborative Learning with Unreliability Adaptation for Semi-Supervised Image Classification

2023-01-01

6

PRE

AI

DOI：10.1016/j.patcog.2022.109032

Original

Original request for help

Save

Abstract

En 中文

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. (c) 2022 Elsevier Ltd. All rights reserved.

Keywords:

Semi -supervised learning

Image classification

Unreliability adaptation

Collaborative learning

Collaborative Learning with Unreliability Adaptation for Semi-Supervised Image Classification

Abstract

Journal

Organization