Object detection is an important task for remote sensing image analysis, which aims to identify and locate objects within captured remote sensing images. Several object detection methods have been proposed, among which Non-maximum suppression (NMS) is an essential ingredient of these methods. Although simple and useful for object detection, the performance of detection methods with NMS will degeneradte when the objects within remote sensing images are dense. One of the main reasons is the presence of severe occlusion in some remote sensing images, which can easily mislead NMS to suppress the nearby candidate box of different object from its central box. To address this problem effectively, we propose to measure the correlation between the candidate box and the central box, from which if these two boxes come from the same object can be estimated. Building on this idea, we propose Correlated NMS, which can adaptively adjust the suppression threshold between the candidate box and its central box based on whether they tend to represent the same object. Experimental results demonstrate the effectiveness of the proposed method.

Variations in both object scale and style under different capture scenes (e.g., downtown, port) greatly enhance the difficulties associated with object detection in aerial images. Although ground sample distance (GSD) provides an apparent clue to address this issue, no existing object detection methods have considered utilizing this useful prior knowledge. In this paper, we propose the first object detection network to incorporate GSD into the object detection modeling process. More specifically, built on a two-stage detection framework, we adopt a GSD identification subnet converting the GSD regression into a probability estimation process, then combine the GSD information with the sizes of Regions of Interest (RoIs) to determine the physical size of objects. The estimated physical size can provide a powerful prior for detection by reweighting the weights from the classification layer of each category to produce RoI-wise enhanced features. Furthermore, to improve the discriminability among categories of similar size and make the inference process more adaptive, the scene information is also considered. The pipeline is flexible enough to be stacked on any two-stage modern detection framework. The improvement over the existing two-stage object detection methods on the DOTA dataset demonstrates the effectiveness of our method.

Deep neural networks have been proven to be a promising way for hyperspectral image (HSI) classification. Their success depends on a premise that source domain (i.e., training) and target domain (i.e., test) samples are identically distributed. However, due to various imaging environments, in practice obvious distribution discrepancy often exists between these two domains, which can dramatically reduce the capacity of the classifier trained in source domain generalizing to target domain. To mitigate this problem, we present a novel deep unsupervised domain adaptation framework for HSI classification, which can simultaneously align the distributions of two domains and learn a classifier in source domain. Firstly, we employ two auto-encoder networks to separately project the samples from two domains into two low-dimensional feature spaces. Then, a multi-level maximum mean discrepancy (MMD) loss is imposed on the feature space to reduce the distribution discrepancy between two domains. Given the resultant features, a classification subnet is further learned to classify the labeled samples in source domain. Since the classifier is trained based on the domain-invariant features, it can well generalize to the target domain. Experimental results on one benchmark cross-domain HSI datasets prove the superior performance of the proposed method.

In hyperspectral image (HSI) classification, domain adaptation (DA) methods have been proved effective to address unsatisfactory classification results caused by the distribution difference between training (i.e., source domain) and testing (i.e., target domain) pixels. However, these methods rely on accurate labels in source domain, and seldom consider the performance drop resulted by noisy label, which often happens since labeling pixel in HSI is a challenging task. To improve the robustness of DA method to label noise, we propose a new unsupervised HSI DA method, which is constructed from both feature-level and classifier-level. First, a linear transformation function is learned in feature-level to align the source (domain) subspace with the target (domain) subspace. Then, a robust low-rank representation based classifier is developed to well cope with the features obtained from the aligned subspace. Since both subspace alignment and the classifier are immune to noisy labels, the proposed method obtains good classification results when confronting with noisy labels in source domain. Experimental results on two DA benchmarks demonstrate the effectiveness of the proposed method.