Abstract-In this paper, we have derived analytic expressions for the phase correlation of downsampled images. We have shown that for downsampled images the signal power in the phase correlation is not concentrated in a single peak, but rather in several coherent peaks mostly adjacent to each other. These coherent peaks correspond to the polyphase transform of a filtered unit impulse centered at the point of registration. The analytic results provide a closed-form solution to subpixel translation estimation, and are used for detailed error analysis. Excellent results have been obtained for subpixel translation estimation of images of different nature and across different spectral bands.

No abstract

Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an end-to-end image compression model to defend adversarial examples: ComDefend. The proposed model consists of a compression convolutional neural network (ComCNN) and a reconstruction convolutional neural network (RecCNN). The ComCNN is used to maintain the structure information of the original image and purify adversarial perturbations. And the RecCNN is used to reconstruct the original image with high quality. In other words, ComDefend can transform the adversarial image to its clean version, which is then fed to the trained classifier. Our method is a pre-processing module, and does not modify the classifier's structure during the whole process. Therefore, it can be combined with other model-specific defense models to jointly improve the classifier's robustness. A series of experiments conducted on MNIST, CIFAR10 and ImageNet show that the proposed method outperforms the state-of-the-art defense methods, and is consistently effective to protect classifiers against adversarial attacks.

The NASA Global‐scale Observations of the Limb and Disk (GOLD) mission has flown an ultraviolet‐imaging spectrograph on SES‐14, a communications satellite in geostationary orbit at 47.5°W longitude. That instrument observes the Earth's far ultraviolet (FUV) airglow at ~134–162 nm using two identical channels. The observations performed include limb scans, stellar occultations, and images of the sunlit and nightside disk from 6:10 to 00:40 universal time each day. Initial analyses reveal interesting and unexpected results as well as the potential for further studies of the Earth's thermosphere‐ionosphere system and its responses to solar‐geomagnetic forcing and atmospheric dynamics. Thermospheric composition ratios for major constituents, O and N2, temperatures near 160 km, and exospheric temperatures are retrieved from the daytime observations. Molecular oxygen (O2) densities are measured using stellar occultations. At night, emission from radiative recombination in the ionospheric F region is used to quantify ionospheric density variations in the equatorial ionization anomaly (EIA). Regions of depleted F region electron density are frequently evident, even during the current solar minimum. These depletions are caused by the “plasma fountain effect” and are associated with the instabilities, scintillations, or “spread F” seen in other types of observations, and GOLD makes unique observations for their study.

No abstract

During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving and augmented reality. However, to train CNNs requires a considerable amount of data, which is difficult to collect and laborious to annotate. Recent advances in computer graphics make it possible to train CNNs on photo-realistic synthetic imagery with computer-generated annotations. Despite this, the domain mismatch between the real images and the synthetic data hinders the models' performance. Hence, we propose a curriculum-style learning approach to minimizing the domain gap in urban scene semantic segmentation. The curriculum domain adaptation solves easy tasks first to infer necessary properties about the target domain; in particular, the first task is to learn global label distributions over images and local distributions over landmark superpixels. These are easy to estimate because images of urban scenes have strong idiosyncrasies (e.g., the size and spatial relations of buildings, streets, cars, etc.). We then train a segmentation network, while regularizing its predictions in the target domain to follow those inferred properties. In experiments, our method outperforms the baselines on two datasets and two backbone networks. We also report extensive ablation studies about our approach.

The most important obstacles facing multidocument summarization include excessive redundancy in source descriptions and the looming shortage of training data. These obstacles prevent encoder-decoder models from being used directly, but optimization-based methods such as determinantal point processes (DPPs) are known to handle them well. In this paper we seek to strengthen a DPP-based method for extractive multi-document summarization by presenting a novel similarity measure inspired by capsule networks. The approach measures redundancy between a pair of sentences based on surface form and semantic information. We show that our DPP system with improved similarity measure performs competitively, outperforming strong summarization baselines on benchmark datasets. Our findings are particularly meaningful for summarizing documents created by multiple authors containing redundant yet lexically diverse expressions. 1

In this paper, we establish the exact relationship between the continuous and the discrete phase difference of two shifted images, and show that their discrete phase difference is a two-dimensional sawtooth signal. Subpixel registration can, thus, be performed directly in the Fourier domain by counting number of cycles of the phase difference matrix along each frequency axis. The subpixel portion is given by the noninteger fraction of the last cycle along each axis. The problem is formulated as an overdetermined homogeneous quadratic cost function under rank constraint for the phase difference, and the shape constraint for the filter that computes the group delay. The optimal tradeoff for imposing the constraints is determined using the method of generalized cross validation. Also, in order to robustify the solution, we assume a mixture model of inlying and outlying estimated shifts and truncate our quadratic cost function using expectation maximization.