Deep CORAL: Correlation Alignment for Deep Domain Adaptation
Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed to compensate fo
- PDF / 398,273 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 85 Downloads / 251 Views
University of Massachusetts Lowell, Lowell, USA [email protected] 2 Boston University, Boston, USA [email protected]
Abstract. Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed to compensate for the degradation in performance due to domain shift. In this paper, we address the case when the target domain is unlabeled, requiring unsupervised adaptation. CORAL [18] is a simple unsupervised domain adaptation method that aligns the second-order statistics of the source and target distributions with a linear transformation. Here, we extend CORAL to learn a nonlinear transformation that aligns correlations of layer activations in deep neural networks (Deep CORAL). Experiments on standard benchmark datasets show state-of-the-art performance. Our code is available at: https://github.com/VisionLearningGroup/CORAL.
1
Introduction
Many machine learning algorithms assume that the training and test data are independent and identically distributed (i.i.d.). However, this assumption rarely holds in practice as the data is likely to change over time and space. Even though state-of-the-art Deep Convolutional Neural Network features are invariant to low level cues to some degree [15,16,19], Donahue et al. [3] showed that they still are susceptible to domain shift. Instead of collecting labeled data and training a new classifier for every possible scenario, unsupervised domain adaptation methods [4,6,17,18,20,21] try to compensate for the degradation in performance by transferring knowledge from labeled source domains to unlabeled target domains. A recently proposed CORAL method [18] aligns the second-order statistics of the source and target distributions with a linear transformation. Even though it is easy to implement, it works well for unsupervised domain adaptation. However, it relies on a linear transformation and is not end-to-end trainable: it needs to first extract features, apply the transformation, and then train an SVM classifier in a separate step. In this work, we extend CORAL to incorporate it directly into deep networks by constructing a differentiable loss function that minimizes the difference between source and target correlations–the CORAL loss. Compared to CORAL, c Springer International Publishing Switzerland 2016 G. Hua and H. J´ egou (Eds.): ECCV 2016 Workshops, Part III, LNCS 9915, pp. 443–450, 2016. DOI: 10.1007/978-3-319-49409-8 35
444
B. Sun and K. Saenko
our proposed Deep CORAL approach learns a non-linear transformation that is more powerful and also works seamlessly with deep CNNs. We evaluate our method on standard benchmark datasets and show state-of-the-art performance.
2
Related Work
Previous techniques for unsupervised adaptation consisted of re-weighting the training point losses to more closely reflect those in the test distribution [9,11] or finding a transformation in a lower-dimensional manifold that brings t
Data Loading...
