Search

We analyze the transformation of a very broad class of metrics that can be expressed in terms of static coordinates. Starting from a general ansatz, we obtain a relation for the parameters in which one can impose further symmetries or restrictions. One of the simplest restrictions leads to FLRW cases, while transforming from the initial static to other static-type coordinates can lead to near horizon coordinates, Wheeler--Regge, and isotropic coordinates, among others. As less restrictive cases, we show an indirect route for obtaining Kruskal-Szekeres within this approach, as well as Lema\^{\i}tre coordinates. We use Schwarzschild spacetime as a prototype for testing the procedure in individual cases. However, application to other spacetimes, such as de-Sitter, Reissner-Nordstr\"{o}m, and Schwarzschild de Sitter, can be readily generalized., Comment: 13 Pages, no figures

Pediatric central nervous system tumors are the leading cause of cancer-related deaths in children. The five-year survival rate for high-grade glioma in children is less than 20%. The development of new treatments is dependent upon multi-institutional collaborative clinical trials requiring reproducible and accurate centralized response assessment. We present the results of the BraTS-PEDs 2023 challenge, the first Brain Tumor Segmentation (BraTS) challenge focused on pediatric brain tumors. This challenge utilized data acquired from multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. BraTS-PEDs 2023 aimed to evaluate volumetric segmentation algorithms for pediatric brain gliomas from magnetic resonance imaging using standardized quantitative performance evaluation metrics employed across the BraTS 2023 challenges. The top-performing AI approaches for pediatric tumor analysis included ensembles of nnU-Net and Swin UNETR, Auto3DSeg, or nnU-Net with a self-supervised framework. The BraTSPEDs 2023 challenge fostered collaboration between clinicians (neuro-oncologists, neuroradiologists) and AI/imaging scientists, promoting faster data sharing and the development of automated volumetric analysis techniques. These advancements could significantly benefit clinical trials and improve the care of children with brain tumors.

Optical continuous glucose monitoring (CGM) systems are emerging for personalized glucose management owing to their lower cost and prolonged durability compared to conventional electrochemical CGMs. Here, we report a computational CGM system, which integrates a biocompatible phosphorescence-based insertable biosensor and a custom-designed phosphorescence lifetime imager (PLI). This compact and cost-effective PLI is designed to capture phosphorescence lifetime images of an insertable sensor through the skin, where the lifetime of the emitted phosphorescence signal is modulated by the local concentration of glucose. Because this phosphorescence signal has a very long lifetime compared to tissue autofluorescence or excitation leakage processes, it completely bypasses these noise sources by measuring the sensor emission over several tens of microseconds after the excitation light is turned off. The lifetime images acquired through the skin are processed by neural network-based models for misalignment-tolerant inference of glucose levels, accurately revealing normal, low (hypoglycemia) and high (hyperglycemia) concentration ranges. Using a 1-mm thick skin phantom mimicking the optical properties of human skin, we performed in vitro testing of the PLI using glucose-spiked samples, yielding 88.8% inference accuracy, also showing resilience to random and unknown misalignments within a lateral distance of ~4.7 mm with respect to the position of the insertable sensor underneath the skin phantom. Furthermore, the PLI accurately identified larger lateral misalignments beyond 5 mm, prompting user intervention for re-alignment. The misalignment-resilient glucose concentration inference capability of this compact and cost-effective phosphorescence lifetime imager makes it an appealing wearable diagnostics tool for real-time tracking of glucose and other biomarkers., Comment: 24 Pages, 4 Figures

Narrow bit-width data formats are key to reducing the computational and storage costs of modern deep learning applications. This paper evaluates Microscaling (MX) data formats that combine a per-block scaling factor with narrow floating-point and integer types for individual elements. MX formats balance the competing needs of hardware efficiency, model accuracy, and user friction. Empirical results on over two dozen benchmarks demonstrate practicality of MX data formats as a drop-in replacement for baseline FP32 for AI inference and training with low user friction. We also show the first instance of training generative language models at sub-8-bit weights, activations, and gradients with minimal accuracy loss and no modifications to the training recipe.

Identification of cracks is essential to assess the structural integrity of concrete infrastructure. However, robust crack segmentation remains a challenging task for computer vision systems due to the diverse appearance of concrete surfaces, variable lighting and weather conditions, and the overlapping of different defects. In particular recent data-driven methods struggle with the limited availability of data, the fine-grained and time-consuming nature of crack annotation, and face subsequent difficulty in generalizing to out-of-distribution samples. In this work, we move past these challenges in a two-fold way. We introduce a high-fidelity crack graphics simulator based on fractals and a corresponding fully-annotated crack dataset. We then complement the latter with a system that learns generalizable representations from simulation, by leveraging both a pointwise mutual information estimate along with adaptive instance normalization as inductive biases. Finally, we empirically highlight how different design choices are symbiotic in bridging the simulation to real gap, and ultimately demonstrate that our introduced system can effectively handle real-world crack segmentation.

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20\%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.

We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. Illustrations contained in field guides deliberately focus on discriminative properties of each species, and can serve as side information to transfer knowledge from seen to unseen bird species. We study two approaches: (1) a contrastive encoding of illustrations, which can be fed into standard zero-shot learning schemes; and (2) a novel method that leverages the fact that illustrations are also images and as such structurally more similar to photographs than other kinds of side information. Our results show that illustrations from field guides, which are readily available for a wide range of species, are indeed a competitive source of side information for zero-shot learning. On a subset of the iNaturalist2021 dataset with 749 seen and 739 unseen species, we obtain a classification accuracy of unseen bird species of $12\%$ @top-1 and $38\%$ @top-10, which shows the potential of field guides for challenging real-world scenarios with many species. Our code is available at https://github.com/ac-rodriguez/zsl_billow, Comment: Accepted to WACV2024

Accurate mapping of oil palm is important for understanding its past and future impact on the environment. We propose to map and count oil palms by estimating tree densities per pixel for large-scale analysis. This allows for fine-grained analysis, for example regarding different planting patterns. To that end, we propose a new, active deep learning method to estimate oil palm density at large scale from Sentinel-2 satellite images, and apply it to generate complete maps for Malaysia and Indonesia. What makes the regression of oil palm density challenging is the need for representative reference data that covers all relevant geographical conditions across a large territory. Specifically for density estimation, generating reference data involves counting individual trees. To keep the associated labelling effort low we propose an active learning (AL) approach that automatically chooses the most relevant samples to be labelled. Our method relies on estimates of the epistemic model uncertainty and of the diversity among samples, making it possible to retrieve an entire batch of relevant samples in a single iteration. Moreover, our algorithm has linear computational complexity and is easily parallelisable to cover large areas. We use our method to compute the first oil palm density map with $10\,$m Ground Sampling Distance (GSD) , for all of Indonesia and Malaysia and for two different years, 2017 and 2019. The maps have a mean absolute error of $\pm$7.3 trees/$ha$, estimated from an independent validation set. We also analyse density variations between different states within a country and compare them to official estimates. According to our estimates there are, in total, $>1.2$ billion oil palms in Indonesia covering $>$15 million $ha$, and $>0.5$ billion oil palms in Malaysia covering $>6$ million $ha$.

We recall that the $k$-Naples parking functions of length $n$ (a generalization of parking functions) are defined by requiring that a car which finds its preferred spot occupied must first back up a spot at a time (up to $k$ spots) before proceeding forward down the street. Note that the parking functions are the specialization of $k$ to $0$. For a fixed $0\leq k\leq n-1$, we define a function $\varphi_k$ which maps a $k$-Naples parking function to the permutation denoting the order in which its cars park. By enumerating the sizes of the fibers of the map $\varphi_k$ we give a new formula for the number of $k$-Naples parking functions as a sum over the permutations of length $n$. We remark that our formula for enumerating $k$-Naples parking functions is not recursive, in contrast to the previously known formula of Christensen et al [CHJ+20]. It can be expressed as the product of the lengths of particular subsequences of permutations, and its specialization to $k=0$ gives a new way to describe the number of parking functions of length $n$. We give a formula for the sizes of the fibers of the map $\varphi_0$, and we provide a recurrence relation for its corresponding logarithmic generating function. Furthermore, we relate the $q$-analog of our formula to a new statistic that we denote $\texttt{area}_k$ and call the $k$-Naples area statistic, the specialization of which to $k=0$ gives the $\texttt{area}$ statistic on parking functions., Comment: 17 pages, 2 figures, 1 table

In this work we present a Four-Wheeled Independent Drive and Steering (4WIDS) robot named AGRO and a method of controlling its orientation while airborne using wheel reaction torques. This is the first documented use of independently steerable wheels to both drive on the ground and achieve aerial attitude control when thrown. Inspired by a cat's self-righting reflex, this capability was developed to allow emergency response personnel to rapidly deploy AGRO by throwing it over walls and fences or through windows without the risk of it landing upside down. It also allows AGRO to drive off of ledges and ensure it lands on all four wheels. We have demonstrated a successful thrown deployment of AGRO. A novel parametrization and singularity analysis of 4WIDS kinematics reveals independent yaw authority with simultaneous adjustment of the ratio between roll and pitch authority. Simple PD controllers allow for stabilization of roll, pitch, and yaw. These controllers were tested in a simulation using derived dynamic equations of motion, then implemented on the AGRO prototype. An experiment comparing a controlled and non-controlled fall was conducted in which AGRO was dropped from a height of 0.85 m with an initial roll and pitch angle of 16 degrees and -23 degrees respectively. With the controller enabled, AGRO can use the reaction torque from its wheels to stabilize its orientation within 402 milliseconds., Comment: IROS 2020, Final Accepted Version

We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets. Our main motivation is the recognition of animal species for ecological applications such as biodiversity modelling, which is challenging because of long-tailed species distributions due to rare species, and strong dataset biases such as repetitive scene background in camera traps. To counteract these challenges, we propose a visual attention mechanism that is supervised via keypoint annotations that highlight important object parts. This privileged information, implemented as a novel privileged pooling operation, is only required during training and helps the model to focus on regions that are discriminative. In experiments with three different animal species datasets, we show that deep networks with privileged pooling can use small training sets more efficiently and generalize better., Comment: Updated version with iNaturalist2018 dataset. privileged pooling, supervised attention, training set bias, fine-grained species recognition, camera trap images

Warning. The reading of this paper will send you down many winding roads toward new and exciting research topics enumerating generalized parking functions. Buckle up!, Comment: 9 pages, 6 figures, 1 table

Classical parking functions are defined as the parking preferences for $n$ cars driving (from west to east) down a one-way street containing parking spaces labeled from $1$ to $n$ (from west to east). Cars drive down the street toward their preferred spot and park there if the spot is available. Otherwise, the car continues driving down the street and takes the first available parking space, if such a space exists. If all cars can park using this parking rule, we call the $n$-tuple containing the cars' parking preferences a parking function. In this paper, we introduce a generalization of the parking rule allowing cars whose preferred space is taken to first proceed up to $k$ spaces west of their preferred spot to park before proceeding east if all of those $k$ spaces are occupied. We call parking preferences which allow all cars to park under this new parking rule $k$-Naples parking functions of length $n$. This generalization gives a natural interpolation between classical parking functions, the case when $k=0$, and all $n$-tuples of positive integers $1$ to $n$, the case when $k\geq n-1$. Our main result provides a recursive formula for counting $k$-Naples parking functions of length $n$. We also give a characterization for the $k=1$ case by introducing a new function that maps $1$-Naples parking functions to classical parking functions, i.e. $0$-Naples parking functions. Lastly, we present a bijection between $k$-Naples parking functions of length $n$ whose entries are in weakly decreasing order and a family of signature Dyck paths., Comment: 15 pages, 9 figures