Robust Multi-label Image Classification with Semi-Supervised Learning and Active Learning

Sun, Fuming; Xu, Meixiang; Jiang, Xiaojun

doi:10.1007/978-3-319-14442-9_56

Cited by 1 publication

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aiming at improving the existing models by incrementally selecting and annotating the most informative unlabeled samples, Active Learning (AL) has been well studied in the past few decades [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], and applied to various kind of vision tasks, such as image/video categorization [13], [14], [15], [16], [17], text/web classification [18], [19], [20], image/video retrieval [21], [22], etc. In the AL methods [3], [4], [5], classifier/model is first initialized with a relatively small set of labeled training samples.…”

Section: Introductionmentioning

confidence: 99%

Cost-Effective Active Learning for Deep Image Classification

Wang

Zhang

et al. 2017

IEEE Trans. Circuits Syst. Video Technol.

572

367

View full text Add to dashboard Cite

Abstract-Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing active learning methods in two aspects. First, we incorporate deep convolutional neural networks into active learning. Through the properly designed framework, the feature representation and the classifier can be simultaneously updated with progressively annotated informative samples. Second, we present a cost-effective sample selection strategy to improve the classification performance with less manual annotations. Unlike traditional methods focusing on only the uncertain samples of low prediction confidence, we especially discover the large amount of high confidence samples from the unlabeled set for feature learning. Specifically, these high confidence samples are automatically selected and iteratively assigned pseudo-labels. We thus call our framework " Cost-Effective Active Learning" (CEAL) standing for the two advantages. Extensive experiments demonstrate that the proposed CEAL framework can achieve promising results on two challenging image classification datasets, i.e., face recognition on CACD database [1] and object categorization on Caltech-256 [2].

show abstract