Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization

By Yi Yang, Zhigang Ma, Feiping Nie, Xiaojun Chang, Alexander G. Hauptmann. International Journal of Computer Vision, 2015

523 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/eaa8c743ac2ec922edb99fce089dbf34d1472747

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

The Power of Ensembles for Active Learning in Image Classification (2018, background): “Commonly used acquisition functions are based on criteria such as uncertainty of prediction ([16], [32], [62]), coverage of the data space ([52]), unanimity of a committee ([30]), expected error, or variance reduction ([25], [33]).”
Learning Active Learning from Data (2017, background): “Uncertainty sampling (US) US has been reported to be successful in numerous scenarios and settings and despite its simplicity, it often works remarkably well [32, 15, 27, 34, 17, 24].”
Pattern Recognition (2018, unknown): “The accuracy of gait recognition suffers a lot when human appearance changes greatly because of viewpoint, clothing and carried objects.”
Generative Adversarial Active Learning (2017, methodology): “In our case, we can substitute the ﬁrst term in the objective function (3) with a diversity measure such as proposed in (Yang et al., 2014; Hoi et al., 2009), thus maximizing the diversity.”
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color (2021, background): “…beneﬁcial for robust representation learning, in correspondence with the idea of sample diversity in the active learning literature (Brinker, 2003; Yang et al., 2015). pos-ent ’s lack of signiﬁcance, on the other hand, indicates that the degree of speciﬁcation offered by the POS tagset might be…”
Learning Loss for Active Learning (2019, methodology): “algorithm to the pool, and [57, 9, 15] formulate the subset selection as a discrete optimization problem.”
Where am I in the dark: Exploring active transfer learning on the use of indoor localization based on thermal imaging (2016, background): “[28,29] mined label correlations and visual similarities to selected data as diverse as possible to overcome the issue of small labeled data in the seed set.”
Robust Joint Graph Sparse Coding for Unsupervised Spectral Feature Selection (2017, background): “Moreover, it has been shown that the intrinsic dimensionality of high-dimensional data is typically small [5]–[9].”
Active Learning for Convolutional Neural Networks: A Core-Set Approach (2017, background): “Both Elhamifar et al. (2013) and Yang et al. (2015) design a discrete optimization problem for this purpose and use its convex surrogate.”