Multi-exposure fusion combines bracketed exposure captures into a single image with enhanced details from a large dynamic range. It is an effective and resource-efficient way to obtain a high dynamic range image, which has broad applications. Despite significant advancements in the field, existing methods often struggle with artifacts and fall short of preserving the local details while being compute-intensive. Previous similar training-free approaches compute weight maps for fusing the exposure stack, which requires finding how well-exposed each image is. In this paper, we work on the fundamentals to define a novel, well-exposedness function along with a tile-based processing approach. Our approach provides improved image quality with better detail recovery. It outperforms the current state-of-the-art training-free methods both qualitatively and quantitatively while being better suited for onboard processing.

The attribution problem, that is the problem of attributing a model’s prediction to its base features, is well-studied. We extend the notion of attribution to also apply to feature interactions. The Shapley value is a commonly used method to attribute a model’s prediction to its base features. We propose a generalization of the Shapley value called Shapley-Taylor index that attributes the model’s prediction to interactions of subsets of features up to some size $k$. The method is analogous to how the truncated Taylor Series decomposes the function value at a certain point using its derivatives at a different point. In fact, we show that the Shapley Taylor index is equal to the Taylor Series of the multilinear extension of the set-theoretic behavior of the model. We axiomatize this method using the standard Shapley axioms—linearity, dummy, symmetry and efficiency—and an additional axiom that we call the interaction distribution axiom. This new axiom explicitly characterizes how interactions are distributed for a class of functions that model pure interaction. We contrast the Shapley-Taylor index against the previously proposed Shapley Interaction index from the cooperative game theory literature. We also apply the Shapley Taylor index to three models and identify interesting qualitative insights.

Dynamic neural networks are becoming increasingly common, and yet it is hard to implement them efficiently. On-the-fly operation batching for such models is sub-optimal and suffers from run time overheads, while writing manually batched versions can be hard and error-prone. To address this we extend TensorFlow with pfor, a parallel-for loop optimized using static loop vectorization. With pfor, users can express computation using nested loops and conditional constructs, but get performance resembling that of a manually batched version. Benchmarks demonstrate speedups of one to two orders of magnitude on range of tasks, from jacobian computation, to Graph Neural Networks.

There has been great interest in creating probabilistic programming languages to simplify the coding of statistical tasks; however, there still does not exist a formal language that simultaneously provides (1) continuous probability distributions, (2) the ability to naturally express custom probabilistic models, and (3) probability density functions (PDFs). This collection of features is necessary for mechanizing fundamental statistical techniques. We formalize the first probabilistic language that exhibits these features, and it serves as a foundational framework for extending the ideas to more general languages. Particularly novel are our type system for absolutely continuous (AC) distributions (those which permit PDFs) and our PDF calculation procedure, which calculates PDF s for a large class of AC distributions. Our formalization paves the way toward the rigorous encoding of powerful statistical reformulations.

Delay-tolerant network (DTN) architectures have recently been proposed as a means to enable efficient routing of messages in vehicular area networks (VANETs), which are characterized by alternating periods of connectivity and disconnection. Under such architectures, when multihop connectivity is available, messages propagate at the speed of radio over connected vehicles. On the other hand, when vehicles are disconnected, messages are carried by vehicles and propagate at vehicle speed. Our goal in this paper is to analytically determine what gains are achieved by DTN architectures and under which conditions, using the average message propagation speed as the primary metric of interest. We develop an analytical model for a bidirectional linear network of vehicles, as found on highways. We derive both upper and lower bounds on the average message propagation speed by exploiting a connection with the classical pattern-matching problem in probability theory. The bounds reveal an interesting phase transition behavior. Specifically, we find out that, below a certain critical threshold, which is a function of the traffic density in each direction, the average message speed is the same as the average vehicle speed, i.e., DTN architectures provide no gain. On the other hand, we determine another threshold above which the average message speed quickly increases as a function of traffic density and approaches radio speed. Based on the bounds, we also develop an approximation model for the average message propagation speed that we validate through numerical simulations.

SUMMARY: The advent of next-generation sequencing for functional genomics has given rise to quantities of sequence information that are often so large that they are difficult to handle. Moreover, sequence reads from a specific individual can contain sufficient information to potentially identify and genetically characterize that person, raising privacy concerns. In order to address these issues, we have developed the Mapped Read Format (MRF), a compact data summary format for both short and long read alignments that enables the anonymization of confidential sequence information, while allowing one to still carry out many functional genomics studies. We have developed a suite of tools (RSEQtools) that use this format for the analysis of RNA-Seq experiments. These tools consist of a set of modules that perform common tasks such as calculating gene expression values, generating signal tracks of mapped reads and segmenting that signal into actively transcribed regions. Moreover, the tools can readily be used to build customizable RNA-Seq workflows. In addition to the anonymization afforded by MRF, this format also facilitates the decoupling of the alignment of reads from downstream analyses. AVAILABILITY AND IMPLEMENTATION: RSEQtools is implemented in C and the source code is available at http://rseqtools.gersteinlab.org/.

Enabling safety in vehicles is an ongoing challenge for the automotive sector. One approach towards enhancing safety is to increase knowledge within a vehicle of the actions of vehicles in the vicinity. Increased awareness is essential for activating the safety systems to take evasive or precautionary actions in the event of an incident. Wireless radio communication has emerged as a key enabler for exchanging safety information. Several initiatives across the world have considered various radio communication technologies to implement safety communication. However, there are significant constraints to utilizing wireless radio communication. In this article, we discuss briefly the challenges in enabling safety communication with wireless radio in the context of vehicular networks. We introduce the on-going work in utilizing free space optical communications as an enabler for inter-vehicle safety communication. As a first step, we compare with the current 802.11 standard implementation for achievable performance. Given that the two technologies are inherently different, directional versus omni-directional, we seek to identify the scenarios where each technology is best suited. Particularly, we compare packet delivery ratio (PDR), throughput and average packet delay of the two enabling technologies, under assumptions, in the context of increasing vehicle traffic density. Our results demonstrate that a directional technology such as free-space optics is less susceptible to contention scenarios. As a result, the performance in high density scenarios is better than that can be achieved from using omni-directional long-range technologies such as 802.11.

At Google, experimentation is practically a mantra; we evaluate almost every change that potentially affects what our users experience. Such changes include not only obvious user-visible changes such as modifications to a user interface, but also more subtle changes such as different machine learning algorithms that might affect ranking or content selection. Our insatiable appetite for experimentation has led us to tackle the problems of how to run more experiments, how to run experiments that produce better decisions, and how to run them faster. In this paper, we describe Google's overlapping experiment infrastructure that is a key component to solving these problems. In addition, because an experiment infrastructure alone is insufficient, we also discuss the associated tools and educational processes required to use it effectively. We conclude by describing trends that show the success of this overall experimental environment. While the paper specifically describes the experiment system and experimental processes we have in place at Google, we believe they can be generalized and applied by any entity interested in using experimentation to improve search engines and other web applications.

In this paper, we present an analytical model for delay tolerant message propagation in a dynamic vehicular network. The analysis provides upper and lower bounds for message propagation as function of traffic density, vehicle speed and radio range. The model is an extension of previous work which considered a particular network setting. The results from the analytical model are compared with simulation results for various vehicular traffic densities. The work demonstrates that increased mobility of vehicles actually aids in messaging contrary to the expectation that it would be a hindrance due to frequent topology changes. An increase in vehicle speed from 0 m/s to 20 m/s results in a corresponding increase in message propagation rate of 200 m/s for vehicular density of 25 vehicles/km.

Abstract We obtain improved upper and lower bounds on the best case and random case transport capacities of wireless networks under the Protocol Model of communication in Reference [ 1 ]. These results bracket the best case transport capacity to within a factor of $\sqrt8$ for wireless networks on a disk. This is done by identifying larger exclusion regions for receivers. The general result on exclusion regions can also be applied to arbitrary wireless footprints, including those arising from directional antennas, thus obtaining superior bounds for such technologies too. Copyright © 2004 John Wiley & Sons, Ltd.