The acquisition of sufficient labeled samples is often a significant challenge in the field of remote sensing imagery, due to the time-consuming and high cost nature of field data collection. As a result, researchers ...
详细信息
ISBN:
(纸本)9789819784929;9789819784936
The acquisition of sufficient labeled samples is often a significant challenge in the field of remote sensing imagery, due to the time-consuming and high cost nature of field data collection. As a result, researchers have recently aimed to explore and develop effective few-shot learning methods that can overcome the shortage of labeled data in remote sensing imagery. Few-shot learning aims to enable machine learning algorithms to learn from a few labeled data or even from a single sample. The classification of remote sensing data is challenging because of the high interclass similarity and intraclass diversity found within remote sensing scenes. Direct computation of similarities between query and support data in current methods can lead to confusion. We propose a discriminative representation-based classifier (DRC) for few-shot remote sensing scene categorization to overcome this issue. Specifically, we introduce two discriminative constraint terms in the objective function: intraclass and interclass constraints. The intraclass constraint term enhances the concentration of the learned representation vectors in same class learned by the classifier, while the interclass constraint term reduces the correlation between the representation vectors of different categories. The experimental findings on the difficult remote sensing datasets NWPU-RESISC45 and RSD46-WHU demonstrate that our proposed DRC method delivers cutting-edge results in few-shot remote sensing scene image classification.
Collaborative representation is an effective way to design classifiers for many practical applications. In this paper, we propose a novel classifier, called the prior knowledge-based probabilistic collaborative repres...
详细信息
Collaborative representation is an effective way to design classifiers for many practical applications. In this paper, we propose a novel classifier, called the prior knowledge-based probabilistic collaborative representation-based classifier (PKPCRC), for visual recognition. Compared with existing classifiers which use the collaborative representation strategy, the proposed PKPCRC further includes characteristics of training samples of each class as prior knowledge. Four types of prior knowledge are developed from the perspectives of image distance and representation capacity. They adaptively accommodate the contribution of each class and result in an accurate representation to classify a query sample. Experiments and comparisons on four challenging databases demonstrate that PKPCRC outperforms several state-of-the-art classifiers.
Nearest regularized subspace (NRS) has been recently proposed for hyperspectral image (HSI) classification. The NRS outperforms both collaborative representation classification and sparse representation-based techniqu...
详细信息
Nearest regularized subspace (NRS) has been recently proposed for hyperspectral image (HSI) classification. The NRS outperforms both collaborative representation classification and sparse representation-based techniques because the NRS makes use of the distance-weighted Tikhonov regularization to ensure appropriate representation from similar samples within-class. However, typical NRS only considers Euclidean distance, which may be suboptimal to resolve the problem of sensitivity in the absolute magnitude of a spectrum. An NRS-Manhattan distance (MD) strategy is proposed for HSI classification. The proposed distance metric controls over magnitude change and emphasizes the shape of the spectrum. Furthermore, the MD metric uses the entire information of the spectral bands in full dimensionality of the HSI pixels, which makes NRS-MD a more efficient pixelwise classifier. Validations are done with several hyperspectral data, i.e., Indian Pines, Botswana, Salinas, and Houston. Results demonstrate that the proposed NRS-MD is superior to other state-of-the-art methods. (C) 2019 Society of Photo-Optical Instrumentation Engineers (SPIE)
Sparse coding aims to find a parsimonious representation of an example given an observation matrix or dictionary. In this regard, Orthogonal Matching Pursuit (OMP) provides an intuitive, simple and fast approximation ...
详细信息
Sparse coding aims to find a parsimonious representation of an example given an observation matrix or dictionary. In this regard, Orthogonal Matching Pursuit (OMP) provides an intuitive, simple and fast approximation of the optimal solution. However, its main building block is anchored on the minimization of the Mean Squared Error cost function (MSE). This approach is only optimal if the errors are distributed according to a Gaussian distribution without samples that strongly deviate from the main mode, i.e. outliers. If such assumption is violated, the sparse code will likely be biased and performance will degrade accordingly. In this paper, we introduce five robust variants of OMP (RobOMP) fully based on the theory of M-Estimators under a linear model. The proposed framework exploits efficient Iteratively Reweighted Least Squares (IRLS) techniques to mitigate the effect of outliers and emphasize the samples corresponding to the main mode of the data. This is done adaptively via a learned weight vector that models the distribution of the data in a robust manner. Experiments on synthetic data under several noise distributions and image recognition under different combinations of occlusion and missing pixels thoroughly detail the superiority of RobOMP over MSE-based approaches and similar robust alternatives. We also introduce a denoising framework based on robust, sparse and redundant representations that open the door to potential further applications of the proposed techniques. The five different variants of RobOMP do not require parameter tuning from the user and, hence, constitute principled alternatives to OMP.
暂无评论