Privacy Leakage Avoidance with Switching Ensembles. (arXiv:1911.07921v1 [cs.LG])

We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample belongs to the dataset on which the attacked machine learning model was trained. Several approaches have been developed to mitigate…

Patch augmentation: Towards efficient decision boundaries for neural networks. (arXiv:1911.07922v1 [cs.CV])

In this paper we propose a new augmentation technique, called patch augmentation, that, in our experiments, improves model accuracy and makes networks more robust to adversarial attacks. In brief, this data-independent approach creates new image data based on image/label pairs, where a patch from one of the two images in the pair is superimposed on…

Search for dark matter induced de-excitation of $^{180}$Ta$\rm ^m$. (arXiv:1911.07865v1 [astro-ph.CO])

Weak-scale dark matter particles, in collisions with nuclei, can mediate transitions between different nuclear energy levels. In particular, owing to sizeable momentum exchange, dark matter particles can enable de-excitation of nuclear isomers that are extremely long lived with respect to regular radioactive decays. In this paper, we utilize data from a past experiment with $^{180}$Ta$\rm…

Wind-Induced Changes to Surface Gravity Wave Shape in Deep to Intermediate Water. (arXiv:1911.07879v1 [physics.flu-dyn])

Wave shape (i.e. skewness or asymmetry) plays an important role in beach morphology evolution, remote sensing, and ship safety. Wind’s influence on ocean waves has been extensively studied theoretically in the context of growth, but most theories are phase averaged and cannot predict wave shape. Most laboratory and numerical studies similarly focus on wave growth.…

Simulation and Optimization of Mean First Passage Time Problems in 2-D using Numerical Embedded Methods and Perturbation Theory. (arXiv:1911.07842v1 [math.NA])

We develop novel numerical methods and perturbation approaches to determine the mean first passage time (MFPT) for a Brownian particle to be captured by either small stationary or mobile traps inside a bounded 2-D confining domain. Of particular interest is to identify optimal arrangements of small absorbing traps that minimize the average MFPT. Although the…

Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data. (arXiv:1911.07849v1 [cs.CV])

Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformations might never appear (e.g. an upright face with a horizontal nose), current equivariant architectures consider the set of all possible transformations in…

Frequency Separation for Real-World Super-Resolution. (arXiv:1911.07850v1 [eess.IV])

Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic downscaling). While the proposed methods perform well on standard benchmarks, they often fail to produce convincing results in…

RWNE: A Scalable Random-Walk based Network Embedding Framework with Personalized Higher-order Proximity Preserved. (arXiv:1911.07874v1 [cs.LG])

Higher-order proximity preserved network embedding has attracted increasing attention recently. In particular, due to the superior scalability, random-walk based network embedding has also been well developed, which could efficiently explore higher-order neighborhood via multi-hop random walks. However, despite the success of current random-walk based methods, most of them are usually not expressive enough to preserve…

Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks. (arXiv:1911.07883v1 [cs.CV])

Vision-Language Navigation (VLN) is a task where agents learn to navigate following natural language instructions. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches exploit the vision and language features in cross-modal grounding. However, the VLN task remains challenging, since previous works have neglected the rich…