Search

Open-set domain adaptation is a developing and practical solution to training deep networks using unlabeled data which have been collected among unknown data and are under domain shift with other labeled data. This scenario transfers knowledge from a source domain enriched with labeled data to the unlabeled target domain, meanwhile, unknown target samples which are not present in the source domain are separated. Existing methods aim to bridge the domain gap of shared classes between source and target domains in a trustworthy manner and avoid negative transfer learning using keeping away unknown data from the domain alignment step. In this review article, we present a unified framework of theory advances for network risk and a new categorization of open-set domain adaptation along with listing evaluation metrics and popular datasets. Then we accentuate challenges and gaps in existing studies to organize a road map for future research using detailed analysis of investigations. To bring things full circle, we also point out different assumptions and outlooks in the settings of this research area. • For the first time, existing methods in deep domain adaptation with open-set target data are categorized and reviewed. • To produce an optimum upper bound for network risk in the training step, needed theories are presented. • For each category of open-set domain adaptation methods, the problem assumptions along with their algorithms are pointed out. • To present a comparative framework for these methods, their performances, advantages and disadvantages are also examined. • Finally, for paving the research directions in future works, research gaps and challenges are discussed. [ABSTRACT FROM AUTHOR]

Among the Markov random field methods, conditional random fields (CRF) model has shown good results in Synthetic Aperture Radar (SAR) image segmentation. CRF not only directly models the posterior distribution of label field conditioned on images but also allows the interactions between observations. In this paper, we propose a Fast, Weighted CRF (FWCRF) algorithm based on a two-step superpixel generation method. In our method, heterogeneity of intensity in SAR images due to speckle noise and backscattering is considered. The first step is a preprocessing task for suppressing speckle noise which is done by the L0 smoothing algorithm. It is followed by Sobel edge detector to highlight heterogeneous regions and edges. Then SAR image is partitioned into homogeneous and heterogeneous regions by using fast robust fuzzy c-means clustering (FRFCM). Simultaneously, the simple linear iterative clustering (SLIC) algorithm is applied to split the image into superpixels. Next, the superpixels belonging to the same class are merged by using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method. Finally, the SAR image is labelled using the FWCRF algorithm which consists of weighted pairwise potential based on adaptive features and applying FRFCM as an initial segmentation method. The proposed algorithm is evaluated in comparison with other conditional random field schemes. The results of our proposed method demonstrate accuracy improvement in segmentation. [ABSTRACT FROM AUTHOR]

• A new statistical conditional random field is proposed for SAR image segmentation. • The generalized Gaussian distribution of wavelet coefficients is applied in the CRF. • The unary potential is constructed based on the generalized Gaussian distribution. • The Kullback–Leibler distance improves the pairwise potential results. Recently, the conditional random field (CRF) model has been greatly considered in synthetic aperture radar (SAR) image segmentation. This model not only directly considers the posterior distribution of the label field conditioned on images but also gives the interactions between the observations. In this paper, we propose a new CRF-based algorithm for SAR image segmentation. We consider the statistical approach jointly in feature extraction and similarity measurement in the proposed conditional random field model. Using the benefit of the 2-D wavelet transform, we define the generalized Gaussian distribution (GGD) on the wavelet coefficients to extract texture-based features. Then, to improve the CRF potential functions a new unary function is proposed which exactly matches the statistical properties of the wavelet coefficients and produces more accurate parameters for different regions. As the advantage of this function, it is no longer necessary to apply the multinomial logistic regression (MLR) model used in previous CRFs. Moreover, using the Kullback–Leibler distance (KLD) between distribution functions, the similarity measure in our pairwise potential is proposed very effectively and efficiently. The superiority of this scheme is that the similarity measure can be entirely computed using the parameters of the GGD that are typically of small size compared with the feature vectors in the previous methods. Comprehensive experiments on both synthetic and real SAR images indicate that our proposed algorithm achieves accuracy improvement in SAR image segmentation. [ABSTRACT FROM AUTHOR]