基于重建分类网络特征增强的盲域自适应分类器

Blind Domain Adaptation via Reconstruction-Classification network Feature Augmentation

领域自适应算法能解决源域样本与目标域样本分布不同的问题,提高分类性能。但是通常的领域自适应算法都需要预先获取部分目标域样本用于模型训练。而在现实场景中,来自目标域的测试样本在模型训练时是未知的甚至是不可获取的,该问题称为盲领域问题。文章采用重建分类网络(Reconstruction-Classification Network,RCN)运用于盲领域自适应。仅使用源域样本训练源域RCN模型,并利用源域RCN模型重建管道增强目标样本的信息,缩小目标域与源域分布差异。增强后的目标样本通过源域RCN模型的分类管道进行分类。在基准数据集上进行的实验证明,该文的方法在跨域视觉识别方面优于其他最新方法。

Domain adaptive algorithms can solve the problem of different distribution of samples in the source and target domains,and improve the classification performance.But the usual domain adaptive algorithm needs to obtain some target domain samples in advance for model training.In real scenes,the test samples from the target domain are unknown or even unavailable during model training.This problem is called the blind domain problem.In this paper,the Reconstruction Classification Network(RCN)is used in blind domain adaptation.Only the source domain samples are used to train the source domain RCN model,and the source domain RCN model is used to reconstruct the pipeline to enhance the information of the target sample and narrow the distribution difference between the target domain and the source domain.The enhanced target samples are classified by the classification pipeline of the source domain RCN model.Experiments conducted on the benchmark data set prove that the method in this paper is superior to other latest methods in cross-domain visual recognition.