Adversarial Sampling for Active Learning

This paper proposes ASAL, a new GAN based active learning method that generates high entropy samples. Instead of directly annotating the synthetic samples, ASAL searches similar samples from the pool and includes them for training. Hence, the quality of new samples is high and annotations are reliable. To the best of our knowledge, ASAL is the first GAN based AL method applicable to multi-class problems that outperforms random sample selection. Another benefit of ASAL is its small run-time complexity (sub-linear) compared to traditional uncertainty sampling (linear). We present a comprehensive set of experiments on multiple traditional data sets and show that ASAL outperforms similar methods and clearly exceeds the established baseline (random sampling). In the discussion section we analyze in which situations ASAL performs best and why it is sometimes hard to outperform random sample selection.

[1]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[2]  Yi Zhang,et al.  Incorporating Diversity and Density in Active Learning for Relevance Feedback , 2007, ECIR.

[3]  Nikolaos Papanikolopoulos,et al.  Multi-class active learning for image classification , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[6]  Marco Loog,et al.  Active learning using uncertainty information , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[7]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[8]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[9]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[10]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[11]  Prateek Jain,et al.  Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Yi Yang,et al.  Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization , 2015, International Journal of Computer Vision.

[13]  Tao Xiang,et al.  Finding Rare Classes: Active Learning with Generative and Discriminative Models , 2013, IEEE Transactions on Knowledge and Data Engineering.

[14]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[15]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[16]  Xiang Wei,et al.  Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect , 2018, ICLR.

[17]  Arnold W. M. Smeulders,et al.  Active learning using pre-clustering , 2004, ICML.

[18]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[19]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[20]  In So Kweon,et al.  Learning Loss for Active Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  José Bento,et al.  Generative Adversarial Active Learning , 2017, ArXiv.

[22]  Yinda Zhang,et al.  LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop , 2015, ArXiv.

[23]  Nello Cristianini,et al.  Query Learning with Large Margin Classi ersColin , 2000 .

[24]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Silvio Savarese,et al.  Active Learning for Convolutional Neural Networks: A Core-Set Approach , 2017, ICLR.

[26]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[27]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[28]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[29]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[30]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[31]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[32]  Mayank Bawa,et al.  LSH forest: self-tuning indexes for similarity search , 2005, WWW '05.

[33]  Jan C. van Gemert,et al.  Active Decision Boundary Annotation with Deep Generative Models , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[34]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[35]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[36]  J. Lafferty,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[37]  Sanjoy Dasgupta,et al.  A General Agnostic Active Learning Algorithm , 2007, ISAIM.

[38]  John Langford,et al.  Importance weighted active learning , 2008, ICML '09.