Brain-Inspired Model for Incremental Learning Using a Few Examples

Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally. We propose a novel approach to incremental learning inspired by the concept learning model of the hippocampus that represents each image class as centroids and does not suffer from catastrophic forgetting. Classification of a test image is accomplished using the distance of the test image to the n closest centroids. We further demonstrate that our approach can incrementally learn from only a few examples per class. Evaluations of our approach on three class-incremental learning benchmarks: Caltech-101, CUBS-200-2011 and CIFAR-100 for incremental and few-shot incremental learning depict state-of-the-art results in terms of classification accuracy over all learned classes.

[1]  Byoung-Tak Zhang,et al.  Overcoming Catastrophic Forgetting by Incremental Moment Matching , 2017, NIPS.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Pietro Perona,et al.  The Caltech-UCSD Birds-200-2011 Dataset , 2011 .

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

[5]  Adrian Popescu,et al.  DeeSIL: Deep-Shallow Incremental Learning , 2018, ECCV Workshops.

[6]  Paul F. M. J. Verschure,et al.  Proceedings of the 4th International Conference on Biomimetic and Biohybrid Systems - Volume 9222 , 2015 .

[7]  Yandong Guo,et al.  Incremental Classifier Learning with Generative Adversarial Networks , 2018, ArXiv.

[8]  Bolei Zhou,et al.  Places: A 10 Million Image Database for Scene Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Alan Wagner,et al.  CBCL: Brain-Inspired Model for RGB-D Indoor Scene Classification , 2019 .

[10]  Yuxin Peng,et al.  Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification , 2014, ACM Multimedia.

[11]  Cordelia Schmid,et al.  Incremental Learning of Object Detectors without Catastrophic Forgetting , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[12]  Alexander V. Terekhov,et al.  Knowledge Transfer in Deep Block-Modular Neural Networks , 2015, Living Machines.

[13]  Matthieu Guillaumin,et al.  Incremental Learning of NCM Forests for Large-Scale Image Classification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Marcus Rohrbach,et al.  Memory Aware Synapses: Learning what (not) to forget , 2017, ECCV.

[15]  Dahua Lin,et al.  Learning a Unified Classifier Incrementally via Rebalancing , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Christoph H. Lampert,et al.  Curriculum learning of multiple tasks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Stefan Rüping,et al.  Incremental Learning with Support Vector Machines , 2001, ICDM.

[18]  Vasant Honavar,et al.  Learn++: an incremental learning algorithm for supervised neural networks , 2001, IEEE Trans. Syst. Man Cybern. Part C.

[19]  Robi Polikar,et al.  Learn$^{++}$ .NC: Combining Ensemble of Classifiers With Dynamically Weighted Consult-and-Vote for Efficient Incremental Learning of New Classes , 2009, IEEE Transactions on Neural Networks.

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Gabriela Csurka,et al.  Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost , 2012, ECCV.

[22]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[24]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  R. French.  Dynamically constraining connectionist networks to produce distributed, orthogonal representations to reduce catastrophic interference , 2019, Proceedings of the Sixteenth Annual Conference of the Cognitive Science Society.

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

[27]  Yandong Guo,et al.  Large Scale Incremental Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Yoshua Bengio,et al.  An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks , 2013, ICLR.

[29]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[30]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[31]  Philip H. S. Torr,et al.  Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence , 2018, ECCV.

[32]  Ronald Kemker,et al.  FearNet: Brain-Inspired Model for Incremental Learning , 2017, ICLR.

[33]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Ilja Kuzborskij,et al.  From N to N+1: Multiclass Transfer Incremental Learning , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[35]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[36]  Christopher Summerfield,et al.  Comparing continual task learning in minds and machines , 2018, Proceedings of the National Academy of Sciences.

[37]  Cordelia Schmid,et al.  End-to-End Incremental Learning , 2018, ECCV.

[38]  Rama Chellappa,et al.  Learning Without Memorizing , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[40]  Robert M. French,et al.  Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting , 2004, Connect. Sci..

[41]  Gabriela Csurka,et al.  Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[43]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[44]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[45]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[46]  Bradley C. Love,et al.  Building concepts one episode at a time: The hippocampus and concept formation , 2017, Neuroscience Letters.

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