Co-Representation Learning For Classification and Novel Class Detection via Deep Networks

One of the key challenges of performing label prediction over a data stream concerns with the emergence of instances belonging to unobserved class labels over time. Previously, this problem has been addressed by detecting such instances and using them for appropriate classifier adaptation. The fundamental aspect of a novel-class detection strategy relies on the ability of comparison among observed instances to discriminate them into known and unknown classes. Therefore, studies in the past have proposed various metrics suitable for comparison over the observed feature space. Unfortunately, these similarity measures fail to reliably identify distinct regions in observed feature spaces useful for class discrimination and novel-class detection, especially in streams containing high-dimensional data instances such as images and texts. In this paper, we address this key challenge by proposing a semi-supervised multi-task learning framework called \sysname{} which aims to intrinsically search for a latent space suitable for detecting labels of instances from both known and unknown classes. We empirically measure the performance of \sysname{} over multiple real-world image and text datasets and demonstrate its superiority by comparing its performance with existing semi-supervised methods.

[1]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[3]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[5]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[6]  Jiwen Lu,et al.  Discriminative Deep Metric Learning for Face Verification in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[8]  Frédéric Jurie,et al.  PCCA: A new approach for distance learning from sparse pairwise constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[10]  Xiaogang Wang,et al.  DeepID3: Face Recognition with Very Deep Neural Networks , 2015, ArXiv.

[11]  Terrance E. Boult,et al.  Towards Open Set Deep Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Charu C. Aggarwal,et al.  Efficient handling of concept drift and concept evolution over Stream Data , 2016, 2016 IEEE 32nd International Conference on Data Engineering (ICDE).

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

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

[15]  Xiang Yu,et al.  Deep Metric Learning via Lifted Structured Feature Embedding , 2016 .

[16]  Tara N. Sainath,et al.  FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597 , 2012 .

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

[18]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[19]  Bhavani M. Thuraisingham,et al.  Classification and Novel Class Detection in Concept-Drifting Data Streams under Time Constraints , 2011, IEEE Transactions on Knowledge and Data Engineering.

[20]  Graham W. Taylor,et al.  Learning Confidence for Out-of-Distribution Detection in Neural Networks , 2018, ArXiv.

[21]  Zhi-Hua Zhou,et al.  Streaming Classification with Emerging New Class by Class Matrix Sketching , 2017, AAAI.

[22]  R. Srikant,et al.  Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks , 2017, ICLR.

[23]  Lei Shu,et al.  DOC: Deep Open Classification of Text Documents , 2017, EMNLP.

[24]  Latifur Khan,et al.  SAND: Semi-Supervised Adaptive Novel Class Detection and Classification over Data Stream , 2016, AAAI.

[25]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[26]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[27]  Nanning Zheng,et al.  Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[29]  Dacheng Tao,et al.  Classification and Representation Joint Learning via Deep Networks , 2017, IJCAI.