Using Neural Network Formalism to Solve Multiple-Instance Problems

Many objects in the real world are difficult to describe by a single numerical vector of a fixed length, whereas describing them by a set of vectors is more natural. Therefore, Multiple instance learning (MIL) techniques have been constantly gaining on importance throughout last years. MIL formalism represents each object (sample) by a set (bag) of feature vectors (instances) of fixed length where knowledge about objects (e.g., class label) is available on bag level but not necessarily on instance level. Many standard tools including supervised classifiers have been already adapted to MIL setting since the problem got formalized in late nineties. In this work we propose a neural network (NN) based formalism that intuitively bridges the gap between MIL problem definition and the vast existing knowledge-base of standard models and classifiers. We show that the proposed NN formalism is effectively optimizable by a modified back-propagation algorithm and can reveal unknown patterns inside bags. Comparison to eight types of classifiers from the prior art on a set of 14 publicly available benchmark datasets confirms the advantages and accuracy of the proposed solution.

[1]  Qi Zhang,et al.  EM-DD: An Improved Multiple-Instance Learning Technique , 2001, NIPS.

[2]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[3]  Marco Loog,et al.  Multiple instance learning with bag dissimilarities , 2013, Pattern Recognit..

[4]  Bernhard Schölkopf,et al.  Hilbert Space Embeddings and Metrics on Probability Measures , 2009, J. Mach. Learn. Res..

[5]  Tomás Lozano-Pérez,et al.  A Framework for Multiple-Instance Learning , 1997, NIPS.

[6]  Petros Drineas,et al.  On the Nyström Method for Approximating a Gram Matrix for Improved Kernel-Based Learning , 2005, J. Mach. Learn. Res..

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

[8]  Eric Granger,et al.  Multiple instance learning: A survey of problem characteristics and applications , 2016, Pattern Recognit..

[9]  Paul A. Viola,et al.  Multiple Instance Boosting for Object Detection , 2005, NIPS.

[10]  Razvan Pascanu,et al.  Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks , 2013, ECML/PKDD.

[11]  Thomas Hofmann,et al.  Support Vector Machines for Multiple-Instance Learning , 2002, NIPS.

[12]  Marcello Pelillo,et al.  Similarity-Based Pattern Recognition: SIMBAD 2011 , 2011 .

[13]  Bernhard Schölkopf,et al.  Learning from Distributions via Support Measure Machines , 2012, NIPS.

[14]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  Jun Wang,et al.  Solving the Multiple-Instance Problem: A Lazy Learning Approach , 2000, ICML.

[16]  James R. Foulds,et al.  A review of multi-instance learning assumptions , 2010, The Knowledge Engineering Review.

[17]  Jan Ramon,et al.  Multi instance neural networks , 2000, ICML 2000.

[18]  Yixin Chen,et al.  MILES: Multiple-Instance Learning via Embedded Instance Selection , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Zhi-Hua Zhou,et al.  Neural Networks for Multi-Instance Learning , 2002 .

[20]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[21]  David Haussler,et al.  Convolution kernels on discrete structures , 1999 .

[22]  Jaume Amores,et al.  Multiple instance classification: Review, taxonomy and comparative study , 2013, Artif. Intell..

[23]  Thomas Gärtner,et al.  Multi-Instance Kernels , 2002, ICML.

[24]  David M. J. Tax,et al.  Characterizing Multiple Instance Datasets , 2015, SIMBAD.

[25]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.