Deep Active Learning Image Classification Algorithm Based on Class-Wise Self-Knowledge Distillation

Yuliang Pang, Ying Liu, Yu Hao, Yanchao Gong, Daxiang Li, Zhijie Xu

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

The success of image classification techniques based on deep learning relies heavily on a large amount of labeled data. However, the cost of data annotation is often expensive. This paper investigates active learning algorithms for image classification to reduce the cost of data annotation. However, traditional active learning algorithms for image classification suffer from overfitting issues due to training deep neural networks with millions of parameters using a small amount of labeled data. This makes it difficult for the model to effectively assess the information richness of unknown unlabeled samples and is detrimental to the selection of high-value samples. To alleviate these issues, this paper proposes a deep active learning-based image classification algorithm with class-wise self-knowledge distillation. This algorithm reduces overfitting and class-wise variations by matching or distilling the predictive distribution between different samples with the same label during training, thereby enabling a more accurate evaluation of the informativeness of unlabeled data by the active learning algorithm and improving the performance of the classification model. Additionally, an efficient Shuffle Attention mechanism is introduced to improve the sample selection strategy by combining spatial and channel feature information of the images. The proposed algorithm is compared with five active learning baselines on CIFAR10, CIFAR100, SVHN, and FashionMNIST datasets. Experimental results demonstrate the proposed algorithm exhibits superior classification performance.

Original languageEnglish
Title of host publicationAIPR 2023 - 6th International Conference on Artificial Intelligence and Pattern Recognition
PublisherAssociation for Computing Machinery
Pages205-211
Number of pages7
ISBN (Electronic)9798400707674
DOIs
Publication statusPublished - 22 Sept 2023
Externally publishedYes
Event6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023 - Xiamen, China
Duration: 22 Sept 202324 Sept 2023

Publication series

NameACM International Conference Proceeding Series

Conference

Conference6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023
Country/TerritoryChina
CityXiamen
Period22/09/2324/09/23

Keywords

  • Active Learning
  • Image Classification
  • Self-Knowledge Distillation
  • Shuffle Attention

Fingerprint

Dive into the research topics of 'Deep Active Learning Image Classification Algorithm Based on Class-Wise Self-Knowledge Distillation'. Together they form a unique fingerprint.

Cite this