Domain Adaptive Neural Networks for Object Recognition

Abstract

We propose a simple neural network model to deal with the domain adaptation problem in object recognition. Our model incorporates the Maximum Mean Discrepancy (MMD) measure as a regularization in the supervised learning to reduce the distribution mismatch between the source and target domains in the latent space. From experiments, we demonstrate that the MMD regularization is an effective tool to provide good domain adaptation models on both SURF features and raw image pixels of a particular image data set. We also show that our proposed model, preceded by the denoising auto-encoder pretraining, achieves better performance than recent benchmark models on the same data sets. This work represents the first study of MMD measure in the context of neural networks.

References in corpus (2)

• Improving neural networks by preventing co-adaptation of feature detectors
• Frustratingly Easy Domain Adaptation

Cited by in corpus (18)

• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• Deep Visual Domain Adaptation: A Survey
• Revisiting Batch Normalization For Practical Domain Adaptation
• Return of Frustratingly Easy Domain Adaptation
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• Learning Transferable Policies for Monocular Reactive MAV Control
• Cross Modal Distillation for Supervision Transfer
• Knowledge Projection for Deep Neural Networks
• Correlation Alignment by Riemannian Metric for Domain Adaptation
• Cross-Domain Visual Recognition via Domain Adaptive Dictionary Learning
• Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors
• Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
• Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection
• Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification
• Unsupervised Deep Domain Adaptation for Pedestrian Detection
• Conceptual Domain Adaptation Using Deep Learning