Active Decision Boundary Annotation with Deep Generative Models

This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask the oracle to annotate data samples. Instead, we take a profoundly different approach: we ask for annotations of the decision boundary. We achieve this using a deep generative model to create novel instances along a 1d line. A point on the decision boundary is revealed where the instances change class. Experimentally we show on three data sets that our method can be plugged into other active learning schemes, that human oracles can effectively annotate points on the decision boundary, that our method is robust to annotation noise, and that decision boundary annotations improve over annotating data samples.

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

[2]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[3]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[4]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[5]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[6]  Mark Craven,et al.  An Analysis of Active Learning Strategies for Sequence Labeling Tasks , 2008, EMNLP.

[7]  Dale Schuurmans,et al.  Discriminative Batch Mode Active Learning , 2007, NIPS.

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

[9]  Amin Karbasi,et al.  Near-Optimal Active Learning of Halfspaces via Query Synthesis in the Noisy Setting , 2016, AAAI.

[10]  David A. Cohn,et al.  Training Connectionist Networks with Queries and Selective Sampling , 1989, NIPS.

[11]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[12]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[13]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[14]  Bo Du,et al.  Multi-label Active Learning Based on Maximum Correntropy Criterion: Towards Robust and Discriminative Labeling , 2016, ECCV.

[15]  Kristen Grauman,et al.  Fine-Grained Visual Comparisons with Local Learning , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Joachim Denzler,et al.  Active learning and discovery of object categories in the presence of unnameable instances , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Cees Snoek,et al.  Spot On: Action Localization from Pointly-Supervised Proposals , 2016, ECCV.

[18]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[19]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[20]  H. Sebastian Seung,et al.  Query by committee , 1992, COLT '92.

[21]  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.

[22]  Arnold W. M. Smeulders,et al.  Structured Receptive Fields in CNNs , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Cees Snoek,et al.  Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[24]  Xiangliang Zhang,et al.  Efficient Active Learning of Halfspaces via Query Synthesis , 2015, AAAI.

[25]  David D. Lewis,et al.  Heterogeneous Uncertainty Sampling for Supervised Learning , 1994, ICML.

[26]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[27]  Brian Mac Namee,et al.  Model-Free and Model-Based Active Learning for Regression , 2016, UKCI.

[28]  Joachim Denzler,et al.  Selecting Influential Examples: Active Learning with Expected Model Output Changes , 2014, ECCV.

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

[30]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[31]  Andrew Owens,et al.  Ambient Sound Provides Supervision for Visual Learning , 2016, ECCV.

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

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

[34]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

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

[36]  ChengXiang Zhai,et al.  Active feedback in ad hoc information retrieval , 2005, SIGIR '05.

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

[38]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.

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

[40]  Alexei A. Efros,et al.  Context Encoders: Feature Learning by Inpainting , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Maria Eugenia Ramirez-Loaiza,et al.  Active learning: an empirical study of common baselines , 2017, Data Mining and Knowledge Discovery.

[42]  Amin Karbasi,et al.  Dimension Coupling: Optimal Active Learning of Halfspaces via Query Synthesis , 2016, ArXiv.

[43]  Jingbo Zhu,et al.  Active Learning With Sampling by Uncertainty and Density for Data Annotations , 2010, IEEE Transactions on Audio, Speech, and Language Processing.