Nowadays, data is represented by vectors. Retrieving those vectors, among millions and billions, that are similar to a given query is a ubiquitous problem, known as similarity search, of relevance for a wide range of applications. Graph-based indices are currently the best performing techniques for billion-scale similarity search. However, their random-access memory pattern presents challenges to realize their full potential. In this work, we present new techniques and systems for creating faster and smaller graph-based indices. To this end, we introduce a novel vector compression method, Locally-adaptive Vector Quantization (LVQ), that uses per-vector scaling and scalar quantization to improve search performance with fast similarity computations and a reduced effective bandwidth, while decreasing memory footprint and barely impacting accuracy. LVQ, when combined with a new high-performance computing system for graph-based similarity search, establishes the new state of the art in terms of performance and memory footprint. For billions of vectors, LVQ outcompetes the second-best alternatives: (1) in the low-memory regime, by up to 20.7x in throughput with up to a 3x memory footprint reduction, and (2) in the high-throughput regime by 5.8x with 1.4x less memory.

Multi - image alignment, bringing a group of images into common register, is an ubiquitous problem and the first step of many applications in a wide variety of domains. As a result, a great amount of effort is being invested in developing efficient multi-image alignment algorithms. Little has been done, however, to answer fundamental practical questions such as: what is the comparative performance of existing methods? is there still room for improvement? under which conditions should one technique be preferred over another? does adding more images or prior image information improve the registration results? In this work, we present a thorough analysis and evaluation of the main multi-image alignment methods which, combined with theoretical limits in multi-image alignment performance, allows us to organize them under a common framework and provide practical answers to these essential questions.

This work provides an overview of an education and technology monitoring system developed at Plan Ceibal, a nationwide initiative created to enable technology enhanced learning in Uruguay. Plan Ceibal currently offers one-to-one access to technology and connectivity to every student and teacher (from primary and secondary education) as well as a comprehensive set of educational software platforms. All these resources generate massive amounts of data about the progress and style of students learning. This work introduces the conceptual framework, design and preliminary results of the Big Data Center for learning analytics currently being developed at Plan Ceibal. This initiative is focused on exploiting these datasets and conducting advanced analytics to support the educational system. To this aim, a 360 degrees profile will be built including information characterizing the user's online behavior as well as a set of technology enhanced learning factors. These profiles will be studied both at user (e.g., student or teacher) and larger scale levels (e.g., per school or school system), addressing both the need of understanding how technology is being used for learning as well as to provide accurate feedback to support evidence based educational policies.

The 2nd LAK Failathon will build on the successful event in 2016 and extend the workshop beyond discussing individual experiences of failure to exploring how the field can improve, particularly regarding the creation and use of evidence.

This poster will be a chance for a wider LAK audience to engage with the 2nd LAK Failathon workshop. Both of these will build on the successful Failathon event in 2016 and extend beyond discussing individual experiences of failure to exploring how the field can improve, particularly regarding the creation and use of evidence.

Deeper exploration of the brain's vast synaptic networks will require new tools for high-throughput structural and molecular profiling of the diverse populations of synapses that compose those networks. Fluorescence microscopy (FM) and electron microscopy (EM) offer complementary advantages and disadvantages for single-synapse analysis. FM combines exquisite molecular discrimination capacities with high speed and low cost, but rigorous discrimination between synaptic and non-synaptic fluorescence signals is challenging. In contrast, EM remains the gold standard for reliable identification of a synapse, but offers only limited molecular discrimination and is slow and costly. To develop and test single-synapse image analysis methods, we have used datasets from conjugate array tomography (cAT), which provides voxel-conjugate FM and EM (annotated) images of the same individual synapses. We report a novel unsupervised probabilistic method for detection of synapses from multiplex FM (muxFM) image data, and evaluate this method both by comparison to EM gold standard annotated data and by examining its capacity to reproduce known important features of cortical synapse distributions. The proposed probabilistic model-based synapse detector accepts molecular-morphological synapse models as user queries, and delivers a volumetric map of the probability that each voxel represents part of a synapse. Taking human annotation of cAT EM data as ground truth, we show that our algorithm detects synapses from muxFM data alone as successfully as human annotators seeing only the muxFM data, and accurately reproduces known architectural features of cortical synapse distributions. This approach opens the door to data-driven discovery of new synapse types and their density. We suggest that our probabilistic synapse detector will also be useful for analysis of standard confocal and super-resolution FM images, where EM cross-validation is not practical.

Building high dynamic range (HDR) images by combining photographs captured with different exposure times present several drawbacks, such as the need for global alignment and motion estimation in order to avoid ghosting artifacts. The concept of spatially varying pixel exposures (SVE) proposed by Nayar et al. enables to capture in only one shot a very large range of exposures while avoiding these limitations. In this paper, we propose a novel approach to generate HDR images from a single shot acquired with spatially varying pixel exposures. The proposed method makes use of the assumption stating that the distribution of patches in an image is well represented by a Gaussian Mixture Model. Drawing on a precise modeling of the camera acquisition noise, we extend the piecewise linear estimation strategy developed by Yu et al. for image restoration. The proposed method permits to reconstruct an irradiance image by simultaneously estimating saturated and under-exposed pixels and denoising existing ones, showing significant improvements over existing approaches.

Since the seminal work of Mann and Picard in 1995, the standard way to build high dynamic range (HDR) images from regular cameras has been to combine a reduced number of photographs captured with different exposure times. The algorithms proposed in the literature differ in the strategy used to combine these frames. Several experimental studies comparing their performances have been reported, showing in particular that a maximum likelihood estimation yields the best results in terms of mean squared error. However, no theoretical study aiming at establishing the performance limits of the HDR estimation problem has been conducted. Another common aspect of all HDR estimation approaches is that they discard saturated values. In this paper, we address these two issues. More precisely, we derive theoretical bounds for the performance of unbiased estimators for the HDR estimation problem. The unbiasedness hypothesis is motivated by the fact that most of the existing estimators, among them the best performing and most well known, are nearly unbiased. Moreover, we show that, even with a small number of photographs, the maximum likelihood estimator performs extremely close to these bounds. As a second contribution, we propose a general strategy for integrating the information provided by saturated pixels in the estimation process, hence improving the estimation results. Finally, we analyze the sensitivity of the HDR estimation process to camera parameters, and we show that small errors in the camera calibration process may severely degrade the estimation results.

Modern digital camera sensors capture only a limited amplitude and frequency range of the irradiance of a scene. A recent trend is to acquire and combine multiple images to raise the quality of the final image. Multi-image techniques are used in high dynamic range processing, where multiple exposure times are used to reconstruct the full range of irradiance. With multi-image superresolution, the difference between sampling grids caused by the motion of the camera is used to generate a high resolution image. It is possible to combine these two processes into one to generate a superresolved image with a full dynamic range. In this paper, we study the reconstruction error of high dynamic range superresolution imaging without regularization, under an affine motion hypothesis. From this study, we deduce a strategy for choosing the number of images and the exposure times, which makes the unregularized problem well conditioned. With these acquisition parameters, if the affine motion hypothesis holds and sufficiently long exposure time is available, the recovery of all the amplitude and frequency content of the scene irradiance is guaranteed.

High dynamic range (HDR) images are usually generated by combining multiple photographs acquired with different exposure times. This approach, while effective, suffers from various drawbacks. The irradiance estimation is performed by combining, for each pixel, different exposure values at the same spatial position. This estimation scheme does not take advantage of the redundancy present in most images. Moreover, images must be perfectly aligned and objects must be in the exact same position in all frames in order to combine the different exposures. In this work, we propose a new HDR image generation approach that simultaneously copes with these problems and exploits image redundancy to produce a denoised result. A reference image is chosen and a patch-based approach is used to find similar pixels that are then combined for the irradiance estimation. This patch-based approach permits to obtain a denoised result and is robust to image misalignments and object motions. Results show significant improvements in terms of noise reduction over previous HDR image generation techniques, while being robust to motion and changes between the exposures.