Multi-class active learning for image classification

By Ajay J. Joshi, Fatih Murat Porikli, N. Papanikolopoulos. 2009

835 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors (2018, background): “Approaches include maximum entropy (Joshi et al., 2009), distance from the decision boundary (Tong and Koller, 2001), pseudo labelling high conﬁdence examples (Wang et al., 2017), and mixtures of information density and uncertainty measures (Li and Guo, 2013).”
Deep Bayesian Active Learning with Image Data (2017, methodology): “Using ideas from previous research in active learning of low dimensional data (Tong, 2001), Joshi et al. (2009) used “margin-based uncertainty” and extracted probabilistic outputs from support vector machines (SVM) (Cortes & Vapnik, 1995).”
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning (2020, background): “The latter was later extended to a multi-class SVM based approach (Joshi et al., 2009), however still based on multiple binary classiﬁers.”
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics (2020, methodology): “Finally, we also compare with our implementation of the following methods for data selection from prior work (discussed in §7): forgetting (Toneva et al., 2018), AFLite (LeBras et al., 2020), AL-uncertainty (Joshi et al., 2009), and AL-greedyK (Sener and Savarese, 2018).”
We Don’t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification (2016, background): “Previous active learning work has mainly focussed on image classification [25, 26, 27, 39], and freeform region labelling [45, 54, 55].”
Cost-Effective Active Learning for Deep Image Classification (2017, methodology): “These approaches usually sequentially select the informative samples relying on the probability estimation [6], [39] or prior information [8] to minimize the generalization error of the trained classiﬁer over the unlabeled data.”
Learning Loss for Active Learning (2019, background): “The uncertainty approach [26, 19, 55, 52, 49, 4] defines and measures the quantity of uncertainty to select uncertain data points, while the diversity approach [45, 37, 15, 5] selects diverse data points that represent the whole distribution of the unlabeled pool.”
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].”
What Do I Annotate Next? An Empirical Study of Active Learning for Action Localization (2018, background): “computer vision tasks, such as image classification [4,22,25,36,37,53] and object detection [64], or to construct large-scale image and video datasets [16,66,72].”
Learning by Asking Questions (2017, background): “Common selection criteria include entropy [25], boosting the margin for classifiers [1, 12] and expected informativeness [20].”
Active Learning for Convolutional Neural Networks: A Core-Set Approach (2017, methodology): “It covers acquisition functions such as information theoretical methods (MacKay, 1992), ensemble approaches (McCallumzy & Nigamy, 1998; Freund et al., 1997) and uncertainty based methods (Tong & Koller, 2001; Joshi et al., 2009; Li & Guo, 2013).”
Uncertainty in Deep Learning (2016, methodology): “image data, a task which has been extremely challenging so far with very sparse existing literature [Holub et al., 2008; Joshi et al., 2009; Li and Guo, 2013; Zhu et al., 2003].”
I Have Seen Enough: Transferring Parts Across Categories (2016, background): “Many data selection strategies have been proposed, based on uncertainty and entropy [48], used in [7, 23, 25, 36], or diversity and representativeness [24].”
Active learning and discovery of object categories in the presence of unnameable instances (2015, background): “Thus, we believe that changes in continuous scores are more meaningful, especially in early stages of learning.”
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization (2015, background): “…School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA F. Nie (B) The Center for OPTical IMagery Analysis and Learning, Northwestern Polytechnical University, Xi’an, China e-mail: feipingnie@gmail.com Keywords Active learning · Uncertainty sampling · Diversity maximization”