Search

Recent works on SLAM extend their pose graphs with higher-level semantic concepts like Rooms exploiting relationships between them, to provide, not only a richer representation of the situation/environment but also to improve the accuracy of its estimation. Concretely, our previous work, Situational Graphs (S-Graphs+), a pioneer in jointly leveraging semantic relationships in the factor optimization process, relies on semantic entities such as Planes and Rooms, whose relationship is mathematically defined. Nevertheless, there is no unique approach to finding all the hidden patterns in lower-level factor-graphs that correspond to high-level concepts of different natures. It is currently tackled with ad-hoc algorithms, which limits its graph expressiveness. To overcome this limitation, in this work, we propose an algorithm based on Graph Neural Networks for learning high-level semantic-relational concepts that can be inferred from the low-level factor graph. Given a set of mapped Planes our algorithm is capable of inferring Room entities relating to the Planes. Additionally, to demonstrate the versatility of our method, our algorithm can infer an additional semantic-relational concept, i.e. Wall, and its relationship with its Planes. We validate our method in both simulated and real datasets demonstrating improved performance over two baseline approaches. Furthermore, we integrate our method into the S-Graphs+ algorithm providing improved pose and map accuracy compared to the baseline while further enhancing the scene representation.

In this paper, we focus on semantic segmentation method for point clouds of urban scenes. Our fundamental concept revolves around the collaborative utilization of diverse scene representations to benefit from different context information and network architectures. To this end, the proposed network architecture, called APNet, is split into two branches: a point cloud branch and an aerial image branch which input is generated from a point cloud. To leverage the different properties of each branch, we employ a geometry-aware fusion module that is learned to combine the results of each branch. Additional separate losses for each branch avoid that one branch dominates the results, ensure the best performance for each branch individually and explicitly define the input domain of the fusion network assuring it only performs data fusion. Our experiments demonstrate that the fusion output consistently outperforms the individual network branches and that APNet achieves state-of-the-art performance of 65.2 mIoU on the SensatUrban dataset. Upon acceptance, the source code will be made accessible., Comment: Accepted by ICCV Workshop 2023 and selected as an oral

We consider the problem of approximating the regression function from noisy vector-valued data by an online learning algorithm using an appropriate reproducing kernel Hilbert space (RKHS) as prior. In an online algorithm, i.i.d. samples become available one by one by a random process and are successively processed to build approximations to the regression function. We are interested in the asymptotic performance of such online approximation algorithms and show that the expected squared error in the RKHS norm can be bounded by $C^2 (m+1)^{-s/(2+s)}$, where $m$ is the current number of processed data, the parameter $0

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

Some autoregressive models exhibit in-context learning capabilities: being able to learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. The origins of this phenomenon are still poorly understood. Here we analyze a series of Transformer models trained to perform synthetic sequence prediction tasks, and discover that standard next-token prediction error minimization gives rise to a subsidiary learning algorithm that adjusts the model as new inputs are revealed. We show that this process corresponds to gradient-based optimization of a principled objective function, which leads to strong generalization performance on unseen sequences. Our findings explain in-context learning as a product of autoregressive loss minimization and inform the design of new optimization-based Transformer layers.

Recognising reinforced concrete defects (RCDs) is a crucial element for determining the structural integrity, traffic safety and durability of bridges. However, most of the existing datasets in the RCD domain are derived from a small number of bridges acquired in specific camera poses, lighting conditions and with fixed hardware. These limitations question the usability of models trained on such open-source data in real-world scenarios. We address this problem by testing such models on our "dacl1k" dataset, a highly diverse RCD dataset for multi-label classification based on building inspections including 1,474 images. Thereby, we trained the models on different combinations of open-source data (meta datasets) which were subsequently evaluated both extrinsically and intrinsically. During extrinsic evaluation, we report metrics on dacl1k and the meta datasets. The performance analysis on dacl1k shows practical usability of the meta data, where the best model shows an Exact Match Ratio of 32%. Additionally, we conduct an intrinsic evaluation by clustering the bottleneck features of the best model derived from the extrinsic evaluation in order to find out, if the model has learned distinguishing datasets or the classes (RCDs) which is the aspired goal. The dacl1k dataset and our trained models will be made publicly available, enabling researchers and practitioners to put their models to the real-world test.

Recent architectural developments have enabled recurrent neural networks (RNNs) to reach and even surpass the performance of Transformers on certain sequence modeling tasks. These modern RNNs feature a prominent design pattern: linear recurrent layers interconnected by feedforward paths with multiplicative gating. Here, we show how RNNs equipped with these two design elements can exactly implement (linear) self-attention, the main building block of Transformers. By reverse-engineering a set of trained RNNs, we find that gradient descent in practice discovers our construction. In particular, we examine RNNs trained to solve simple in-context learning tasks on which Transformers are known to excel and find that gradient descent instills in our RNNs the same attention-based in-context learning algorithm used by Transformers. Our findings highlight the importance of multiplicative interactions in neural networks and suggest that certain RNNs might be unexpectedly implementing attention under the hood.

We have performed a study of several cesium oven designs. A comparison between recirculating (or sticking-wall) or collimating (or reemitting-wall) ovens is made in order to extract the most efficient design in terms of beam brightness. Unfortunately, non-reproducible behaviors have been observed, and the most often observed output flux is similar to the sticking-wall case, which is the lowest theoretical value of the two cases, with a beam brightness close to $10^{18}$ at.sr$^{-1}$.s$^{-1}$.cm$^{-2}$. The reason of this universally observed behavior is unclear despite having tested several materials for the collimating tube. Conclusion on possible improved design based on sticking of cesium on several (un)cleaned surface is given., Comment: This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Rev Sci Instrum 1 April 2022; 93 (4): 043302 and may be found at https://pubs.aip.org/aip/rsi/article/93/4/043302/2848701

Trapped ions in radio-frequency traps are among the leading approaches for realizing quantum computers, due to high-fidelity quantum gates and long coherence times. However, the use of radio-frequencies presents a number of challenges to scaling, including requiring compatibility of chips with high voltages, managing power dissipation and restricting transport and placement of ions. By replacing the radio-frequency field with a 3 T magnetic field, we here realize a micro-fabricated Penning ion trap which removes these restrictions. We demonstrate full quantum control of an ion in this setting, as well as the ability to transport the ion arbitrarily in the trapping plane above the chip. This unique feature of the Penning micro-trap approach opens up a modification of the Quantum CCD architecture with improved connectivity and flexibility, facilitating the realization of large-scale trapped-ion quantum computing, quantum simulation and quantum sensing.

Established surgical navigation systems for pedicle screw placement have been proven to be accurate, but still reveal limitations in registration or surgical guidance. Registration of preoperative data to the intraoperative anatomy remains a time-consuming, error-prone task that includes exposure to harmful radiation. Surgical guidance through conventional displays has well-known drawbacks, as information cannot be presented in-situ and from the surgeon's perspective. Consequently, radiation-free and more automatic registration methods with subsequent surgeon-centric navigation feedback are desirable. In this work, we present an approach that automatically solves the registration problem for lumbar spinal fusion surgery in a radiation-free manner. A deep neural network was trained to segment the lumbar spine and simultaneously predict its orientation, yielding an initial pose for preoperative models, which then is refined for each vertebra individually and updated in real-time with GPU acceleration while handling surgeon occlusions. An intuitive surgical guidance is provided thanks to the integration into an augmented reality based navigation system. The registration method was verified on a public dataset with a mean of 96\% successful registrations, a target registration error of 2.73 mm, a screw trajectory error of 1.79{\deg} and a screw entry point error of 2.43 mm. Additionally, the whole pipeline was validated in an ex-vivo surgery, yielding a 100\% screw accuracy and a registration accuracy of 1.20 mm. Our results meet clinical demands and emphasize the potential of RGB-D data for fully automatic registration approaches in combination with augmented reality guidance.

Retrieving relevant multimedia content is one of the main problems in a world that is increasingly data-driven. With the proliferation of drones, high quality aerial footage is now available to a wide audience for the first time. Integrating this footage into applications can enable GPS-less geo-localisation or location correction. In this paper, we present an orientation-guided training framework for UAV-view geo-localisation. Through hierarchical localisation orientations of the UAV images are estimated in relation to the satellite imagery. We propose a lightweight prediction module for these pseudo labels which predicts the orientation between the different views based on the contrastive learned embeddings. We experimentally demonstrate that this prediction supports the training and outperforms previous approaches. The extracted pseudo-labels also enable aligned rotation of the satellite image as augmentation to further strengthen the generalisation. During inference, we no longer need this orientation module, which means that no additional computations are required. We achieve state-of-the-art results on both the University-1652 and University-160k datasets.

The population of radio pulsars is observed to demonstrate certain polarization properties not explained by the conventional picture of pulsar polarization, namely frequency evolution of polarization, deviations of the linear polarization angle from a curve of geometric origins and the presence of features in the circular polarization. We present the partial-coherence model as a way to explain the co-occurrence of these features and to provide an origin for circular polarization in radio pulsar profiles. We describe the mathematics of the model and demonstrate how it can explain these observed features, both on a population level and for the idiosyncrasies of individual pulsars. The partial coherence model can account for complex polarization behaviour, enabling improved access to information about pulsar geometries. We discuss the scientific implications of this for our understanding of pulsar radio emission and propagation., Comment: 15 pages, 10 figures

We present a comprehensive study of the rotational and emission properties of PSR J0738$-$4042 using a combination of observations taken by the Deep Space Network, Hartebeesthoek, Parkes (Murriyang) and Molonglo observatories between 1972 and 2023. Our timing of the pulsar is motivated by previously reported profile/spin-down events that occurred in September 2005 and December 2015, which result in an anomalously large braking index of $n = 23300 \pm 1800$. Using a Gaussian process regression framework, we develop continuous models for the evolution of the pulsar spin-down rate ($\dot{\nu}$) and profile shape. We find that the pulse profile variations are similar regardless of radio observing frequency and polarisation. Small-scale differences can be ascribed to changes in the interstellar medium along the line of sight and frequency-dependent changes in magnetospheric radio emission height. No new correlated spin-down or profile events were identified in our extended dataset. However, we found that the disappearance of a bright emission component in the leading edge of archival profiles between 1981-1988 was not associated with a substantial change in $\dot{\nu}$. This marks a notable departure from the previous profile/spin-down events in this pulsar. We discuss the challenges these observations pose for physical models and conclude that interactions between the pulsar and in-falling asteroids or a form of magnetospheric state-switching with a long periodicity are plausible explanations., Comment: 14 pages, 8 figures. Fixed typo on page 5. Accepted for publication in MNRAS

We present an extension to the iterative Boltzmann inversion method to generate coarse-grained models with three-body intramolecular potentials that can reproduce correlations in structural distribution functions. The coarse-grained structural distribution functions are computed using kernel density estimates to produce analytically differentiable distribution functions with controllable smoothening via the kernel bandwidth parameters. Bicubic interpolation is used to accurately interpolate the three-body potentials trained by the method. To demonstrate this new approach, a coarse-grained model of polyethylene is constructed in which each bead represents an ethylene monomer. The resulting model reproduces the radial density function as well as the joint probability distribution of bond-length and bond-angles sampled from target atomistic simulations with only a 10% increase in the computational cost compared to models with independent bond-length and bond-angle potentials. Analysis of the predicted crystallization kinetics of the model developed by the new approach reveals that the bandwidth parameters can be tuned to accelerate the modeling of polymer crystallization. Specifically, computing target RDF with larger bandwidth slows down the secondary crystallization, and increasing the bandwidth in $\theta$-direction of bond-length and bond-angle distribution reduces the primary crystallization rate., Comment: To be submitted; 31 pages; 8 figures