A new active labeling method for deep learning

By Dan Wang, Yi Shang. 2014

423 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

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

1. Alekh Agarwal
2. Siddharth Swaroop
3. Richard E. Turner
4. Akshay Krishnamurthy
5. J. Langford
6. Alexander Immer
7. Sergey Levine
8. Runa Eschenhagen

In Computer Vision and Pattern Recognition

1. Richard E. Turner
2. Xiaojun Chang
3. Siddharth Swaroop
4. Mohammad Emtiyaz Khan
5. Runa Eschenhagen
6. Po-Yao (Bernie) Huang
7. Alexander Immer
8. Pingbo Pan

In Statistical and Nonlinear Physics

1. David Lopez-Paz
2. J. Langford
3. Richard E. Turner
4. Mohammad Emtiyaz Khan
5. Siddharth Swaroop
6. Natasa Tagasovska
7. Alexander Immer
8. Akshay Krishnamurthy

Citations in the corpus

• Continual Deep Learning by Functional Regularisation of Memorable Past (2020, methodology): “For binary classification, our approach is equivalent to the “Confidence Sampling” approaches used in the Active Learning literature [4, 36], although in general it differs from them.”
• Fine-tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally (2017, background): “However, the research aiming to integrate active learning with deep learning is sparse: Wang and Shang [25] may be the first to incorporate active learning with deep learning, and based their approach on stacked restricted Boltzmann machines and stacked autoencoders.”
• Single-Model Uncertainties for Deep Learning (2018, background): “…softmax score [35, largest], absolute difference between the two largest softmax scores (functional), softmax entropy (entropy), geometrical margin [80, geometrical], ODIN [50], random network distillation [9, distillation], principal component analysis (PCA), Deep Support Vector Data Description…”
• Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds (2019, background): “ENTROPY [10]: uncertainty-based active learning algorithm that selects the top B examples according to the entropy of the example’s predictive class probability distribution, defined as H((f(x; θ)y)y=1), where H(p) = ∑K i=1 pi ln 1 pi .”
• A Survey of Deep Active Learning (2020, methodology): “re too confident. The softmax response (SR) [166] of the final output is unreliable as a measure of confidence, and the performance of this method will thus be even worse than that of random sampling [165]. A Survey of Deep Active Learning 5 (a) Batch query strategy considering only the amount of in”