English

Object Recognition Based on Amounts of Unlabeled Data

Computer Vision and Pattern Recognition 2019-08-17 v1

Abstract

This paper proposes a novel semi-supervised method on object recognition. First, based on Boost Picking, a universal algorithm, Boost Picking Teaching (BPT), is proposed to train an effective binary-classifier just using a few labeled data and amounts of unlabeled data. Then, an ensemble strategy is detailed to synthesize multiple BPT-trained binary-classifiers to be a high-performance multi-classifier. The rationality of the strategy is also analyzed in theory. Finally, the proposed method is tested on two databases, CIFAR-10 and CIFAR-100. Using 2% labeled data and 98% unlabeled data, the accuracies of the proposed method on the two data sets are 78.39% and 50.77% respectively.

Keywords

Cite

@article{arxiv.1603.07957,
  title  = {Object Recognition Based on Amounts of Unlabeled Data},
  author = {Fuqiang Liu and Fukun Bi and Liang Chen},
  journal= {arXiv preprint arXiv:1603.07957},
  year   = {2019}
}

Comments

16 pages, 6 figures, 2 tables

R2 v1 2026-06-22T13:18:46.524Z