Evidential Deep Active Learning for Semi-Supervised Classification

TL;DR

This paper introduces EDALSSC, a semi-supervised classification method that effectively estimates uncertainty during learning, leading to improved sample selection and performance over existing approaches.

Contribution

It proposes a novel evidential deep active learning framework that quantifies uncertainty for both labeled and unlabeled data, enhancing semi-supervised classification.

Findings

EDALSSC outperforms existing methods on image classification datasets.

The approach effectively balances evidence and class influence in uncertainty estimation.

Experimental results validate the superiority of EDALSSC in semi-supervised learning.

Abstract

Semi-supervised classification based on active learning has made significant progress, but the existing methods often ignore the uncertainty estimation (or reliability) of the prediction results during the learning process, which makes it questionable whether the selected samples can effectively update the model. Hence, this paper proposes an evidential deep active learning approach for semi-supervised classification (EDALSSC). EDALSSC builds a semi-supervised learning framework to simultaneously quantify the uncertainty estimation of labeled and unlabeled data during the learning process. The uncertainty estimation of the former is associated with evidential deep learning, while that of the latter is modeled by combining ignorance information and conflict information of the evidence from the perspective of the T-conorm operator. Furthermore, this article constructs a heuristic method to dynamically balance the influence of evidence and the number of classes on uncertainty estimation to ensure that it does not produce counter-intuitive results in EDALSSC. For the sample selection strategy, EDALSSC selects the sample with the greatest uncertainty estimation that is calculated in the form of a sum when the training loss increases in the latter half of the learning process. Experimental results demonstrate that EDALSSC outperforms existing semi-supervised and supervised active learning approaches on image classification datasets.