Class Equilibrium using Coulomb's Law

Projection algorithms learn a transformation function to project the data from input space to the feature space, with the objective of increasing the inter-class distance. However, increasing the inter-class distance can affect the intra-class distance. Maintaining an optimal inter-class separation among the classes without affecting the intra-class distance of the data distribution is a challenging task. In this paper, inspired by the Coulomb's law of Electrostatics, we propose a new algorithm to compute the equilibrium space of any data distribution where the separation among the classes is optimal. The algorithm further learns the transformation between the input space and equilibrium space to perform classification in the equilibrium space. The performance of the proposed algorithm is evaluated on four publicly available datasets at three different resolutions. It is observed that the proposed algorithm performs well for lowresolution images.

[1]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

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

[3]  Chuanfeng Zhao,et al.  HIBOG: Improving the clustering accuracy by ameliorating dataset with gravitation , 2020, Inf. Sci..

[4]  Wei Li.  An Improved Gravitational Search Algorithm for Optimization Problems , 2019, 2019 Chinese Control And Decision Conference (CCDC).

[5]  Iztok Fister,et al.  On the Potential of the Nature-Inspired Algorithms for Pure Binary Classification , 2020, ICCS.

[6]  L. Sudha,et al.  Nature Inspired Meta-heuristic Optimization Algorithms Capitalized , 2020, 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS).

[7]  Mayank Vatsa,et al.  Discriminative shared transform learning for sketch to image matching , 2021, Pattern Recognit..

[8]  Hadi Sadoghi Yazdi,et al.  Gravitation based classification , 2013, Inf. Sci..

[9]  D. A. Dunnett.  Classical Electrodynamics , 2020, Nature.

[10]  Dongdong Li,et al.  Entropy and gravitation based dynamic radius nearest neighbor classification for imbalanced problem , 2020, Knowl. Based Syst..

[11]  Thomas S. Huang,et al.  Studying Very Low Resolution Recognition Using Deep Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Wei Li,et al.  Hybrid Gravitational Search Algorithm Based on Fuzzy Logic , 2017, IEEE Access.

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

[14]  Chao Zhang,et al.  Low-resolution Visual Recognition via Deep Feature Distillation , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[16]  Sepp Hochreiter,et al.  Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields , 2017, ICLR.

[17]  Fred A. Hamprecht,et al.  Learning Diverse Models: The Coulomb Structured Support Vector Machine , 2016, ECCV.

[18]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Kun She,et al.  A Novel Hierarchical Clustering Approach Based on Universal Gravitation , 2020, Mathematical Problems in Engineering.

[20]  Xiangjian He,et al.  See Clearly in the Distance: Representation Learning GAN for Low Resolution Object Recognition , 2020, IEEE Access.

[21]  Richa Singh,et al.  Face Verification via Class Sparsity Based Supervised Encoding , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Pooja Goyal,et al.  A Novel Fitness Computation Framework for Nature Inspired Classification Algorithms , 2018 .

[23]  Yongguo Liu,et al.  Gravitation Theory Based Model for Multi-Label Classification , 2017, Int. J. Comput. Commun. Control.

[24]  Y. LeCun,et al.  Learning methods for generic object recognition with invariance to pose and lighting , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[25]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[26]  Yong Shi,et al.  A Shrinking-Based Approach for Multi-Dimensional Data Analysis , 2003, VLDB.

[27]  Kazuo Murota,et al.  Electric Network Classifier for Semi-Supervised Learning on Graphs , 2006 .

[28]  Himanshu S. Bhatt,et al.  Submitted to Ieee Transactions on Image Processing 1 Improving Cross-resolution Face Matching Using Ensemble Based Co-transfer Learning , 2022 .

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

[30]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[32]  Klaus Obermayer,et al.  Coulomb Classifiers: Generalizing Support Vector Machines via an Analogy to Electrostatic Systems , 2002, NIPS.

[33]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[34]  Nor Ashidi Mat Isa,et al.  Optimized gravitational-based data clustering algorithm , 2018, Eng. Appl. Artif. Intell..