Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation

Abstract

In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new model called Deep Reconstruction-Classification Network (DRCN), which jointly learns a shared encoding representation for two tasks: i) supervised classification of labeled source data, and ii) unsupervised reconstruction of unlabeled target data.In this way, the learnt representation not only preserves discriminability, but also encodes useful information from the target domain. Our new DRCN model can be optimized by using backpropagation similarly as the standard neural networks. We evaluate the performance of DRCN on a series of cross-domain object recognition tasks, where DRCN provides a considerable improvement (up to ~8% in accuracy) over the prior state-of-the-art algorithms. Interestingly, we also observe that the reconstruction pipeline of DRCN transforms images from the source domain into images whose appearance resembles the target dataset. This suggests that DRCN's performance is due to constructing a single composite representation that encodes information about both the structure of target images and the classification of source images. Finally, we provide a formal analysis to justify the algorithm's objective in domain adaptation context.

to appear in European Conference on Computer Vision (ECCV) 2016

References in corpus (5)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Deep Domain Confusion: Maximizing for Domain Invariance
• Frustratingly Easy Domain Adaptation
• Theano: new features and speed improvements
• One-Shot Adaptation of Supervised Deep Convolutional Models

Cited by in corpus (11)

• Deep Visual Domain Adaptation: A Survey
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• Multi-Representation Adaptation Network for Cross-domain Image Classification
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• Domain Adaptation for Time Series Forecasting via Attention Sharing
• Cycle-consistent Conditional Adversarial Transfer Networks
• Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
• Dynamic Feature Alignment for Semi-supervised Domain Adaptation
• Learning Condensed and Aligned Features for Unsupervised Domain Adaptation Using Label Propagation
• Ensemble Multi-Source Domain Adaptation with Pseudolabels