Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification

Abstract

Conditional Maximum Mean Discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions, thus it has been successfully used for pattern classification. However, CMMD does not work well on complex distributions, especially when the kernel function fails to correctly characterize the difference between intra-class similarity and inter-class similarity. In this paper, a new kernel learning method is proposed to improve the discrimination performance of CMMD. It can be operated with deep network features iteratively and thus denoted as KLN for abbreviation. The CMMD loss and an auto-encoder (AE) are used to learn an injective function. By considering the compound kernel, i.e., the injective function with a characteristic kernel, the effectiveness of CMMD for data category description is enhanced. KLN can simultaneously learn a more expressive kernel and label prediction distribution, thus, it can be used to improve the classification performance in both supervised and semi-supervised learning scenarios. In particular, the kernel-based similarities are iteratively learned on the deep network features, and the algorithm can be implemented in an end-to-end manner. Extensive experiments are conducted on four benchmark datasets, including MNIST, SVHN, CIFAR-10 and CIFAR-100. The results indicate that KLN achieves state-of-the-art classification performance.

References in corpus (20)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Learning Transferable Features with Deep Adaptation Networks
• Striving for Simplicity: The All Convolutional Net
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Semi-Supervised Learning with Deep Generative Models
• Temporal Ensembling for Semi-Supervised Learning
• Deeply-Supervised Nets
• Semi-Supervised Learning with Ladder Networks
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• GETNET: A General End-to-end Two-dimensional CNN Framework for Hyperspectral Image Change Detection
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Generative Moment Matching Networks
• Convolutional Neural Networks Applied to House Numbers Digit Classification
• Triple Generative Adversarial Nets
• All you need is a good init
• A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling
• Conditional Generative Moment-Matching Networks
• Max-margin Deep Generative Models

Cited by in corpus (6)

• Unsupervised Domain Adaptation via Discriminative Manifold Propagation
• Learning Target Domain Specific Classifier for Partial Domain Adaptation
• Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation
• When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights
• Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay
• Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment