Collaborative Learning with Unreliability Adaptation for Semi-Supervised Image Classification

作者：

Highlights：

• Transferring the training experience among constituent networks facilitates semi-supervised image classification.

• We design a collaborative learning mechanism based on unreliability adaptation among constituent networks.

• We improve the complementarity of constituent networks by resisting adversarial perturbation.

• The unreliability adaptation and perturbation-based regularization lead to the superior performance on multiple datasets.

摘要

•Transferring the training experience among constituent networks facilitates semi-supervised image classification.•We design a collaborative learning mechanism based on unreliability adaptation among constituent networks.•We improve the complementarity of constituent networks by resisting adversarial perturbation.•The unreliability adaptation and perturbation-based regularization lead to the superior performance on multiple datasets.

论文关键词：Semi-supervised learning,Image classification,Unreliability adaptation,Collaborative learning

论文评审过程：Received 29 May 2021, Revised 19 May 2022, Accepted 5 September 2022, Available online 11 September 2022, Version of Record 21 September 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.109032