Paper Info
Title
Progressive Feature Alignment for Unsupervised Domain Adaptation
Abstract
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain. To tackle this task, recent approaches resort to discriminative domain transfer in virtue of pseudo-labels to enforce the class-level distribution alignment across the source and target domains. These methods, however, are vulnerable to the error accumulation and thus incapable of preserving cross-domain category consistency, as the pseudo-labeling accuracy is not guaranteed explicitly. In this paper, we propose the Progressive Feature Alignment Network (PFAN) to align the discriminative features across domains progressively and effectively, via exploiting the intra-class variation in the target domain. To be specific, we first develop an Easy-to-Hard Transfer Strategy (EHTS) and an Adaptive Prototype Alignment (APA) step to train our model iteratively and alternatively. Moreover, upon observing that a good domain adaptation usually requires a non-saturated source classifier, we consider a simple yet efficient way to retard the convergence speed of the source classification loss by further involving a temperature variate into the soft-max function. The extensive experimental results reveal that the proposed PFAN exceeds the state-of-the-art performance on three UDA datasets.
Year
DOI
Venue
2019
10.1109/CVPR.2019.00072
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Keywords
DocType
ISSN
Recognition: Detection,Categorization,Retrieval,Deep Learning , Representation Learning
Conference
1063-6919
ISBN
Citations 
PageRank 
978-1-7281-3294-5
14
0.56
References 
Authors
10
8
Name
Order
Citations
PageRank
Chen Chaoqi1151.59
Weiping Xie2231.30
Wen-bing Huang316718.91
Yu Rong411617.89
Xinghao Ding559152.95
Yue Huang631729.82
Tingyang Xu76811.60
Junzhou Huang82182141.43