Related papers: Gnuastro: simulating the exposure map of a pointin…
Data visualization tasks often require multi-step reasoning, and the interpretive strategies experts use, such as decomposing complex goals into smaller subtasks and selectively attending to key chart regions are rarely made explicit.…
We present a scheme to automatically set the precision of floating point variables in an application. We design a framework that profiles applications to measure undesirable numerical behavior at the floating point operation level. We use…
For users, recommendations can sometimes seem odd or counterintuitive. Visualizing recommendations can remove some of this mystery, showing how a recommendation is grouped with other choices. A drawing can also lead a user's eye to other…
We present a Bayesian approach to machine learning with probabilistic programs. In our approach, training on available data is implemented as inference on a hierarchical model. The posterior distribution of model parameters is then used to…
We consider the problem of improving kernel approximation via randomized feature maps. These maps arise as Monte Carlo approximation to integral representations of kernel functions and scale up kernel methods for larger datasets. Based on…
Camera calibration is fundamental to 3D vision, and the choice of calibration pattern greatly affects the accuracy. To address aberration issue, star-shaped pattern has been proposed as alternatives to traditional checkerboard. However,…
Estimating the risk level of adversarial examples is essential for safely deploying machine learning models in the real world. One popular approach for physical-world attacks is to adopt the "sticker-pasting" strategy, which however suffers…
We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…
Current descriptors for global localization often struggle under vast viewpoint or appearance changes. One possible improvement is the addition of topological information on semantic objects. However, handcrafted topological descriptors are…
Estimating errors is a crucial part of any scientific analysis. Whenever a parameter is estimated (model-based or not), an error estimate is necessary. Any parameter estimate that is given without an error estimate is meaningless.…
In this paper we address the statistical problem of testing if a stationary process is Gaussian. The observation consists in a finite sample path of the process. Using a random projection technique introduced and studied in Cuesta-Albertos…
STECKMAP stands for STEllar Content and Kinematics via Maximum A Posteriori likelihood. It is a tool for interpreting galaxy spectra in terms of their stellar populations, through the derivation of their star formation history,…
In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary datasets that potentially contain useful information. We propose the problem of extended few-shot learning to study these…
A powerful data transformation method named guided projections is proposed creating new possibilities to reveal the group structure of high-dimensional data in the presence of noise variables. Utilising projections onto a space spanned by a…
Many aspects of the design trade-off of a space-based instrument and its performance can best be tackled through simulations of the expected observations. The complex interplay of various noise sources in the course of the observations make…
Memory bandwidth is strongly correlated to the complexity of the memory access pattern of a running application. To improve memory performance of applications with irregular and/or unpredictable memory patterns, we need tools to analyze…
This paper introduces a practical and accurate calibration method for camera spectral sensitivity using a diffraction grating. Accurate calibration of camera spectral sensitivity is crucial for various computer vision tasks, including color…
This paper proposes the use of graph pattern matching for investigative graph search, which is the process of searching for and prioritizing persons of interest who may exhibit part or all of a pattern of suspicious behaviors or…
Few-shot segmentation is a task to segment objects or regions of novel classes within an image given only a few annotated examples. In the generalized setting, the task extends to segment both the base and the novel classes. The main…
This work addresses the task of overhead image segmentation when auxiliary ground-level images are available. Recent work has shown that performing joint inference over these two modalities, often called near/remote sensing, can yield…