Find the Best Path: An Efficient and Accurate Classifier for Image Hierarchies

Many methods have been proposed to solve the image classification problem for a large number of categories. Among them, methods based on tree-based representations achieve good trade-off between accuracy and test time efficiency. While focusing on learning a tree-shaped hierarchy and the corresponding set of classifiers, most of them [11, 2, 14] use a greedy prediction algorithm for test time efficiency. We argue that the dramatic decrease in accuracy at high efficiency is caused by the specific design choice of the learning and greedy prediction algorithms. In this work, we propose a classifier which achieves a better trade-off between efficiency and accuracy with a given tree-shaped hierarchy. First, we convert the classification problem as finding the best path in the hierarchy, and a novel branch-and-bound-like algorithm is introduced to efficiently search for the best path. Second, we jointly train the classifiers using a novel Structured SVM (SSVM) formulation with additional bound constraints. As a result, our method achieves a significant 4.65%, 5.43%, and 4.07% (relative 24.82%, 41.64%, and 109.79%) improvement in accuracy at high efficiency compared to state-of-the-art greedy "tree-based" methods [14] on Caltech-256 [15], SUN [32] and Image Net 1K [9] dataset, respectively. Finally, we show that our branch-and-bound-like algorithm naturally ranks the paths in the hierarchy (Fig. 8) so that users can further process them.

[1]  A. Land,et al.  An Automatic Method for Solving Discrete Programming Problems , 1960, 50 Years of Integer Programming.

[2]  Cordelia Schmid,et al.  Constructing Category Hierarchies for Visual Recognition , 2008, ECCV.

[3]  Thomas S. Huang,et al.  Image Classification Using Super-Vector Coding of Local Image Descriptors , 2010, ECCV.

[4]  Thomas Hofmann,et al.  Support vector machine learning for interdependent and structured output spaces , 2004, ICML.

[5]  John Langford,et al.  Conditional Probability Tree Estimation Analysis and Algorithms , 2009, UAI.

[6]  Jonathan Krause,et al.  Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Yihong Gong,et al.  Linear spatial pyramid matching using sparse coding for image classification , 2009, CVPR.

[9]  John Langford,et al.  Error-Correcting Tournaments , 2009, ALT.

[10]  Yihong Gong,et al.  Locality-constrained Linear Coding for image classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Pietro Perona,et al.  Learning and using taxonomies for fast visual categorization , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Thomas G. Dietterich,et al.  Solving Multiclass Learning Problems via Error-Correcting Output Codes , 1994, J. Artif. Intell. Res..

[13]  Daphne Koller,et al.  Discriminative learning of relaxed hierarchy for large-scale visual recognition , 2011, 2011 International Conference on Computer Vision.

[14]  Jason Weston,et al.  Label Embedding Trees for Large Multi-Class Tasks , 2010, NIPS.

[15]  Antonio Torralba,et al.  Sharing features: efficient boosting procedures for multiclass object detection , 2004, CVPR 2004.

[16]  Tao Mei,et al.  Automatic Video Genre Categorization using Hierarchical SVM , 2006, 2006 International Conference on Image Processing.

[17]  Alexander C. Berg,et al.  Fast and Balanced: Efficient Label Tree Learning for Large Scale Object Recognition , 2011, NIPS.

[18]  Daphna Weinshall,et al.  Exploiting Object Hierarchy: Combining Models from Different Category Levels , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[19]  Antonio Criminisi,et al.  Decision Forests for Computer Vision and Medical Image Analysis , 2013, Advances in Computer Vision and Pattern Recognition.

[20]  Jennifer G. Dy,et al.  A hierarchical method for multi-class support vector machines , 2004, ICML.

[21]  Joydeep Ghosh,et al.  Integrating support vector machines in a hierarchical output space decomposition framework , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[22]  Fei-Fei Li,et al.  What Does Classifying More Than 10, 000 Image Categories Tell Us? , 2010, ECCV.

[23]  Ming Yang,et al.  Large-scale image classification: Fast feature extraction and SVM training , 2011, CVPR 2011.

[24]  Yi Yang,et al.  Articulated pose estimation with flexible mixtures-of-parts , 2011, CVPR 2011.

[25]  Robert E. Schapire,et al.  Using output codes to boost multiclass learning problems , 1997, ICML.

[26]  Liang-Tien Chia,et al.  Adaptive hierarchical multi-class SVM classifier for texture-based image classification , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[27]  Ali Farhadi,et al.  Attribute Discovery via Predictable Discriminative Binary Codes , 2012, ECCV.

[28]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[29]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[30]  Ling Li,et al.  Multiclass boosting with repartitioning , 2006, ICML.

[31]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[32]  Yoram Singer,et al.  Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers , 2000, J. Mach. Learn. Res..

[33]  Motoaki Kawanabe,et al.  Efficient Classification of Images with Taxonomies , 2009, ACCV.

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