Self-Paced Learning with Diversity

Self-paced learning (SPL) is a recently proposed learning regime inspired by the learning process of humans and animals that gradually incorporates easy to more complex samples into training. Existing methods are limited in that they ignore an important aspect in learning: diversity. To incorporate this information, we propose an approach called self-paced learning with diversity (SPLD) which formalizes the preference for both easy and diverse samples into a general regularizes This regularization term is independent of the learning objective, and thus can be easily generalized into various learning tasks. Albeit non-convex, the optimization of the variables included in this SPLD regularization term for sample selection can be globally solved in linearithmic time. We demonstrate that our method significantly outperforms the conventional SPL on three real-world datasets. Specifically, SPLD achieves the best MAP so far reported in literature on the Hollywood2 and Olympic Sports datasets.

[1]  Bilge Mutlu,et al.  How Do Humans Teach: On Curriculum Learning and Teaching Dimension , 2011, NIPS.

[2]  Deva Ramanan,et al.  Self-Paced Learning for Long-Term Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[4]  Sumit Basu,et al.  Teaching Classification Boundaries to Humans , 2013, AAAI.

[5]  Deyu Meng,et al.  Easy Samples First: Self-paced Reranking for Zero-Example Multimedia Search , 2014, ACM Multimedia.

[6]  Cordelia Schmid,et al.  Action Recognition with Improved Trajectories , 2013, 2013 IEEE International Conference on Computer Vision.

[7]  Georges Quénot,et al.  TRECVID 2015 - An Overview of the Goals, Tasks, Data, Evaluation Mechanisms and Metrics , 2011, TRECVID.

[8]  J. Friedman.  Stochastic gradient boosting , 2002 .

[9]  Alexander G. Hauptmann,et al.  Temporal Extension of Scale Pyramid and Spatial Pyramid Matching for Action Recognition , 2014, ArXiv.

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  Antonio Torralba,et al.  Are all training examples equally valuable? , 2013, ArXiv.

[12]  Cordelia Schmid,et al.  Actions in context , 2009, CVPR.

[13]  Daphne Koller,et al.  Learning specific-class segmentation from diverse data , 2011, 2011 International Conference on Computer Vision.

[14]  C. Schmid,et al.  Recognizing activities with cluster-trees of tracklets , 2012, BMVC.

[15]  M. Yuan,et al.  Model selection and estimation in regression with grouped variables , 2006 .

[16]  Florian Metze,et al.  CMU-Informedia @ TRECVID 2013 Multimedia Event Detection , 2013 .

[17]  Michael Dorr,et al.  Space-Variant Descriptor Sampling for Action Recognition Based on Saliency and Eye Movements , 2012, ECCV.

[18]  Juan Carlos Niebles,et al.  Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification , 2010, ECCV.

[19]  Teruko Mitamura,et al.  Zero-Example Event Search using MultiModal Pseudo Relevance Feedback , 2014, ICMR.

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

[21]  Fei-Fei Li,et al.  Shifting Weights: Adapting Object Detectors from Image to Video , 2012, NIPS.

[22]  Daphne Koller,et al.  Self-Paced Learning for Latent Variable Models , 2010, NIPS.

[23]  Valentin I. Spitkovsky,et al.  Baby Steps: How “Less is More” in Unsupervised Dependency Parsing , 2009 .

[24]  Alexander G. Hauptmann,et al.  Leveraging high-level and low-level features for multimedia event detection , 2012, ACM Multimedia.

[25]  Yong Jae Lee,et al.  Learning the easy things first: Self-paced visual category discovery , 2011, CVPR 2011.

[26]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Chong-Wah Ngo,et al.  Trajectory-Based Modeling of Human Actions with Motion Reference Points , 2012, ECCV.

[28]  William Brendel,et al.  Learning spatiotemporal graphs of human activities , 2011, 2011 International Conference on Computer Vision.

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

[30]  Patrick Bouthemy,et al.  Better Exploiting Motion for Better Action Recognition , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.