Entropy-based active learning for object recognition
By Alex Holub, Pietro Perona, Michael C. Burl. IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops, 2008
326 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/777b96abef29da63d9b4b1a583fa25c24a5ee029
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
- Serge J. Belongie
- Yarin Gal
- Li Fei-Fei
- Trevor Darrell
- Bernt Schiele
- Pietro Perona
- Andrea Vedaldi
- Sergey Levine
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Andrea Vedaldi
- Ming-Hsuan Yang
- Trevor Darrell
- Dacheng Tao
- Andrew Zisserman
- Xiaogang Wang
- Jitendra Malik
Citations in the corpus
- The Power of Ensembles for Active Learning in Image Classification (2018, methodology): “[26] use expected information gain as acquisition function and evaluate on various datasets using a SVM.”
- Visual Recognition with Humans in the Loop (2010, background): “Active learning algorithms [9–11] interleave training a classifier with asking users to label examples, where the objective is to minimize the total number of labeling tasks.”
- Deep Bayesian Active Learning with Image Data (2017, methodology): “As a result most approaches to active learning have focused on low dimensional problems (Tong, 2001; Hernandez-Lobato & Adams, 2015), with only a handful of exceptions (Zhu et al., 2003; Holub et al., 2008; Joshi et al., 2009) relying on kernel or graph-based approaches to handle high-dimensional da”
- Holistic Network Virtualization and Pervasive Network Intelligence for 6G (2023, background): “The data uncertainty can be measured by entropy [205].”
- Multi-class active learning for image classification (2009, background): “Notably, Holub et al. [9] can implicitly handle multiple example selection through their information-based framework.”
- A survey on instance selection for active learning (2012, background): “– Uncertainty sampling [13,21,93] is often straightforward for probabilistic learning models.”
- Fine-tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally (2017, background): “The literature of general active learning and deep learning is rich and deep [8, 28, 17, 20, 9, 10, 26].”
- 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].”