Search

One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server. Although many studies have been proposed to address this challenge, they only focus on local training and aggregation processes to smooth the changes and fail to achieve high performance with deep learning models. Inspired by the phenomenon of neural collapse, we force each client to be optimized toward an optimal global structure for classification. Specifically, we initialize it as a random simplex Equiangular Tight Frame (ETF) and fix it as the unit optimization target of all clients during the local updating. After guaranteeing all clients are learning to converge to the global optimum, we propose to add a global memory vector for each category to remedy the parameter fluctuation caused by the bias of the intra-class condition distribution among clients. Our experimental results show that our method can improve the performance with faster convergence speed on different-size datasets., Comment: 11 pages, 5 figures

Additional file 1.

Synthetic dimensions, wherein dynamics occurs in a set of internal states, have found great success in recent years in exploring topological effects in cold atoms and photonics. However, the phenomena thus far explored have largely been restricted to the non-interacting or weakly interacting regimes. Here, we extend the synthetic dimensions playbook to strongly interacting systems of Rydberg atoms prepared in optical tweezer arrays. We use precise control over driving microwave fields to introduce a tunable $U(1)$ flux in a four-site lattice of coupled Rydberg levels. We find highly coherent dynamics, in good agreement with theory. Single atoms show oscillatory dynamics controllable by the gauge field. Small arrays of interacting atoms exhibit behavior suggestive of the emergence of ergodic and arrested dynamics in the regimes of intermediate and strong interactions, respectively. These demonstrations pave the way for future explorations of strongly interacting dynamics and many-body phases in Rydberg synthetic lattices., Comment: 6 pages, 4 figures; 6 pages and 5 figures of Supplementary Material

Additional file 1.

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long videos. In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos. Specifically, we introduce a simple but effective video encoder that considers both spatial and temporal context by combining convolution and transformer. Inspired by the recent massive progress in self-supervised learning, we propose a new sequence contrast loss (SCL) applied to two related views obtained by expanding a series of spatio-temporal data in two versions. One is the self-supervised version that optimizes embedding space by minimizing KL-divergence between sequence similarity of two augmented views and prior Gaussian distribution of timestamp distance. The other is the weakly-supervised version that builds more sample pairs among videos using video-level labels by dynamic time wrapping (DTW). Experiments on FineGym, PennAction, and Pouring datasets show that our method outperforms previous state-of-the-art by a large margin for downstream fine-grained action classification and even faster inference. Surprisingly, although without training on paired videos like in previous works, our self-supervised version also shows outstanding performance in video alignment and fine-grained frame retrieval tasks., author conflicts

Modern high-performance semantic segmentation methods employ a heavy backbone and dilated convolution to extract the relevant feature. Although extracting features with both contextual and semantic information is critical for the segmentation tasks, it brings a memory footprint and high computation cost for real-time applications. This paper presents a new model to achieve a trade-off between accuracy/speed for real-time road scene semantic segmentation. Specifically, we proposed a lightweight model named Scale-aware Strip Attention Guided Feature Pyramid Network (S$^2$-FPN). Our network consists of three main modules: Attention Pyramid Fusion (APF) module, Scale-aware Strip Attention Module (SSAM), and Global Feature Upsample (GFU) module. APF adopts an attention mechanisms to learn discriminative multi-scale features and help close the semantic gap between different levels. APF uses the scale-aware attention to encode global context with vertical stripping operation and models the long-range dependencies, which helps relate pixels with similar semantic label. In addition, APF employs channel-wise reweighting block (CRB) to emphasize the channel features. Finally, the decoder of S$^2$-FPN then adopts GFU, which is used to fuse features from APF and the encoder. Extensive experiments have been conducted on two challenging semantic segmentation benchmarks, which demonstrate that our approach achieves better accuracy/speed trade-off with different model settings. The proposed models have achieved a results of 76.2\%mIoU/87.3FPS, 77.4\%mIoU/67FPS, and 77.8\%mIoU/30.5FPS on Cityscapes dataset, and 69.6\%mIoU,71.0\% mIoU, and 74.2\% mIoU on Camvid dataset. The code for this work will be made available at \url{https://github.com/mohamedac29/S2-FPN

The encoder-decoder structure has significantly improved performance in many vision tasks by fusing low-level and high-level feature maps. However, this approach can hardly extract sufficient context information for pixel-wise segmentation. In addition, extracting similar low-level features at multiple scales could lead to redundant information. To tackle these issues, we propose Subspace Pyramid Fusion Network (SPFNet). Specifically, we combine pyramidal module and context aggregation module to exploit the impact of multi-scale/global context information. At first, we construct a Subspace Pyramid Fusion Module (SPFM) based on Reduced Pyramid Pooling (RPP). Then, we propose the Efficient Global Context Aggregation (EGCA) module to capture discriminative features by fusing multi-level global context features. Finally, we add decoder-based subpixel convolution to retrieve the high-resolution feature maps, which can help select category localization details. SPFM learns separate RPP for each feature subspace to capture multi-scale feature representations, which is more useful for semantic segmentation. EGCA adopts shuffle attention mechanism to enhance communication across different sub-features. Experimental results on two well-known semantic segmentation datasets, including Camvid and Cityscapes, show that our proposed method is competitive with other state-of-the-art methods.

Compared to typical multi-sensor systems, monocular 3D object detection has attracted much attention due to its simple configuration. However, there is still a significant gap between LiDAR-based and monocular-based methods. In this paper, we find that the ill-posed nature of monocular imagery can lead to depth ambiguity. Specifically, objects with different depths can appear with the same bounding boxes and similar visual features in the 2D image. Unfortunately, the network cannot accurately distinguish different depths from such non-discriminative visual features, resulting in unstable depth training. To facilitate depth learning, we propose a simple yet effective plug-and-play module, One Bounding Box Multiple Objects (OBMO). Concretely, we add a set of suitable pseudo labels by shifting the 3D bounding box along the viewing frustum. To constrain the pseudo-3D labels to be reasonable, we carefully design two label scoring strategies to represent their quality. In contrast to the original hard depth labels, such soft pseudo labels with quality scores allow the network to learn a reasonable depth range, boosting training stability and thus improving final performance. Extensive experiments on KITTI and Waymo benchmarks show that our method significantly improves state-of-the-art monocular 3D detectors by a significant margin (The improvements under the moderate setting on KITTI validation set are $\mathbf{1.82\sim 10.91\%}$ mAP in BEV and $\mathbf{1.18\sim 9.36\%}$ mAP in 3D}. Codes have been released at https://github.com/mrsempress/OBMO., Comment: 9 pages, 9 figures

Robust cooling and nondestructive imaging are prerequisites for many emerging applications of neutral atoms trapped in optical tweezers, such as their use in quantum information science and analog quantum simulation. The tasks of cooling and imaging can be challenged, however, by the presence of large trap-induced shifts of their respective optical transitions. Here, we explore a system of $^{39}$K atoms trapped in a near-detuned ($780$ nm) optical tweezer, which leads to relatively minor differential (ground vs. excited state) Stark shifts. We demonstrate that simple and robust loading, cooling, and imaging can be achieved through a combined addressing of the D$_\textrm{1}$ and D$_\textrm{2}$ transitions. While imaging on the D$_\textrm{2}$ transition, we can simultaneously apply $\Lambda$-enhanced gray molasses (GM) on the D$_\textrm{1}$ transition, preserving low backgrounds for single-atom imaging through spectral filtering. Using D$_\textrm{1}$ cooling during and after trap loading, we demonstrate enhanced loading efficiencies as well as cooling to low temperatures. These results suggest a simple and robust path for loading and cooling large arrays of potassium atoms in optical tweezers through the use of resource-efficient near-detuned optical tweezers and GM cooling., Comment: 8 pages, 4 figures, and 2-page Supplementary Materials

Intraoperative data may improve models predicting postoperative events. We evaluated the effect of incorporating intraoperative variables to the existing preoperative model on the predictive performance of the model for coronary artery bypass graft.We analyzed 378 572 isolated coronary artery bypass graft cases performed across 1083 centers, using the national Society of Thoracic Surgeons Adult Cardiac Surgery Database between 2014 and 2016. Outcomes were operative mortality, 5 postoperative complications, and composite representation of all events. We fitted models by logistic regression or extreme gradient boosting (XGBoost). For each modeling approach, we used preoperative only, intraoperative only, or pre+intraoperative variables. We developed 84 models with unique combinations of the 3 variable sets, 2 variable selection methods, 2 modeling approaches, and 7 outcomes. Each model was tested in 20 iterations of 70:30 stratified random splitting into development/testing samples. Model performances were evaluated on the testing dataset using the C statistic, area under the precision-recall curve, and calibration metrics, including the Brier score.The mean patient age was 65.3 years, and 24.7% were women. Operative mortality, excluding intraoperative death, occurred in 1.9%. In all outcomes, models that considered pre+intraoperative variables demonstrated significantly improved Brier score and area under the precision-recall curve compared with models considering pre or intraoperative variables alone. XGBoost without external variable selection had the best C statistics, Brier score, and area under the precision-recall curve values in 4 of the 7 outcomes (mortality, renal failure, prolonged ventilation, and composite) compared with logistic regression models with or without variable selection. Based on the calibration plots, risk restratification for mortality showed that the logistic regression model underestimated the risk in 11 114 patients (9.8%) and overestimated in 12 005 patients (10.6%). In contrast, the XGBoost model underestimated the risk in 7218 patients (6.4%) and overestimated in 0 patients (0%).In isolated coronary artery bypass graft, adding intraoperative variables to preoperative variables resulted in improved predictions of all 7 outcomes. Risk models based on XGBoost may provide a better prediction of adverse events to guide clinical care.

A topological $θ$-term in gauge theories, including quantum chromodynamics in 3+1 dimensions, gives rise to a sign problem that makes classical Monte Carlo simulations impractical. Quantum simulations are not subject to such sign problems and are a promising approach to studying these theories in the future. In the near term, it is interesting to study simpler models that retain some of the physical phenomena of interest and their implementation on quantum hardware. For example, dimensionally-reducing gauge theories on small spatial tori produces quantum mechanical models which, despite being relatively simple to solve, retain interesting vacuum and symmetry structures from the parent gauge theories. Here we consider quantum mechanical particle-on-a-circle models, related by dimensional reduction to the 1+1d Schwinger model, that possess a $θ$-term and realize an 't Hooft anomaly or global inconsistency at $θ= π$. These models also exhibit the related phenomena of spontaneous symmetry breaking and instanton-anti-instanton interference in real time. We propose an experimental scheme for the real-time simulation of a particle on a circle with a $θ$-term and a $\mathbb{Z}_n$ potential using a synthetic dimension encoded in a Rydberg atom. Simulating the Rydberg atom with realistic experimental parameters, we demonstrate that the essential physics can be well-captured by the experiment, with expected behavior in the tunneling rate as a function of $θ$. Similar phenomena and observables can also arise in more complex quantum mechanical models connected to higher-dimensional nonabelian gauge theories by dimensional reduction., 25 pages, 11 figures; minor changes and refs added, version accepted for publication in PRD

In order to solve the multi-objective optimization problem, this paper proposes a multi-objective cross-entropy optimization (MOCEO) algorithm based on the original single-objective cross-entropy (CE) optimization algorithm. Situations, with a low probability for optimal point, and also, locations with a high probability to fall into local optimum after tested with standard test function ZDT4 and ZDT6 problems. The algorithm is then introduced an improved method called disturbance, including recombination, variance disturbance and varying population size. Each operation contains a variable parameter. Appropriate selection of parameters can maximize the optimization ability. A set of optimal parameters is designed and the answers are verified by a comparative study with other meta-heuristic optimization algorithms such as NSGA-II, SPEA2, MOEA/D and PAES in similar conditions. The results indicate that those improvements are effective and the algorithm proposed in this paper is superior to other algorithms. It has the advantages of strong searching ability and high robustness which is applicable to challenging difficulties with unknown search spaces.

In order to solve the multi-objective optimization problem, this paper proposes a multi-objective cross-entropy (CE) optimization algorithm based on the original single target cross-entropy optimization algorithm. Considering that the CE algorithm is easy to fall into the local optimal solution, as well as the algorithm's search ability is not strong enough, continue to propose a method of segmenting population size, and the effectiveness of this method is proved by experiments. This improved algorithm is named as s-MOCE. At the same time, the individual selection mechanism is adopted to retain the elite individuals in the evolution process and extracts the distribution information through the elite retention strategy to constantly correct the parameters of the normal distribution probability model of the algorithm. Comparing the improved CE algorithm in terms of HV (hyper-volume) index with other well-known algorithms like NSGA-II, dMOPSO, MOEA/D and PAES using the 9 kinds of standard test functions WFG1-WFG9. The results prove that the algorithm proposed in this paper is superior to other algorithms. It has the advantages of fast convergence speed, strong searching ability, and high robustness.

Cross-Entropy (CE) algorithm was originally designed to solve the problem of rare event simulation, and later was promoted to solve the single-objective optimization problem. But this paper attempts to solve the multi-objective optimization problem by using the Cross-Entropy algorithm. As a new heuristic stochastic optimization algorithm, there is no need to optimize the problem with gradient but only adaptability. The cross-entropy optimization algorithm has attracted widespread academic attention due to its low computational complexity and high robustness. Aiming at the problem that the CE algorithm is efficient but the accuracy of solving some questions is still muted, a mixed CEGA algorithm is proposed. First, the characteristics of the NSGA-II algorithm are used to further improve the performance of the CE algorithm. Secondly, using the method of segmenting population size, more accurate results can be obtained with the same numbers of calculation times. Finally, by comparing 11 kinds of standard test functions with 5 kinds of classical multi-objective optimization algorithms, the improved algorithm shows higher accuracy and stronger global search capabilities than other original methods.

Surgical patients are at high risk of developing postoperative cognitive dysfunction (POCD) and postoperative delirium (POD). POCD and POD are associated with increased morbidity and mortality and worsening functional outcomes leading to severe socioeconomic consequences for the patient and the society in general. Magnetic resonance imaging (MRI) offers a unique opportunity to study the anatomy and function of the brain. MRI thus plays an important role in elucidating the neuronal component of POCD and POD. Our aim has been to systematically gather MRI findings that are related to POCD and POD. Systematic searches were conducted in PubMed, EMBASE, and PsycINFO: MRI studies investigating patients with POCD as identified by perioperative cognitive testing or patients with delirium identified postoperatively by the Confusion Assessment Method. A total of ten eligible papers were included with a total of 269 surgical patients, 36 patient controls, and 55 healthy controls who all underwent MRI examination. These studies suggested that reduction of thalamic and hippocampal volumes and reduction of cerebral blood flow may be associated with POCD, while presurgery/preexisting and postoperative white matter pathology may be associated with POD. However, the evidence from these studies is rather weak. Future MRI studies are warranted to verify the current findings.

We consider a collection of independent random variables that are identically distributed, except for a small subset which follows a different, anomalous distribution. We study the problem of detecting which random variables in the collection are governed by the anomalous distribution. Recent work proposes to solve this problem by conducting hypothesis tests based on mixed observations (e.g. linear combinations) of the random variables. Recognizing the connection between taking mixed observations and compressed sensing, we view the problem as recovering the "support" (index set) of the anomalous random variables from multiple measurement vectors (MMVs). Many algorithms have been developed for recovering jointly sparse signals and their support from MMVs. We establish the theoretical and empirical effectiveness of these algorithms at detecting anomalies. We also extend the LASSO algorithm to an MMV version for our purpose. Further, we perform experiments on synthetic data, consisting of samples from the random variables, to explore the trade-off between the number of mixed observations per sample and the number of samples required to detect anomalies., Comment: 27 pages, 9 figures. Incorporates reviewer feedback, additional experiments, and additional figures

While single measurement vector (SMV) models have been widely studied in signal processing, there is a surging interest in addressing the multiple measurement vectors (MMV) problem. In the MMV setting, more than one measurement vector is available and the multiple signals to be recovered share some commonalities such as a common support. Applications in which MMV is a naturally occurring phenomenon include online streaming, medical imaging, and video recovery. This work presents a stochastic iterative algorithm for the support recovery of jointly sparse corrupted MMV. We present a variant of the Sparse Randomized Kaczmarz algorithm for corrupted MMV and compare our proposed method with an existing Kaczmarz type algorithm for MMV problems. We also showcase the usefulness of our approach in the online (streaming) setting and provide empirical evidence that suggests the robustness of the proposed method to the distribution of the corruption and the number of corruptions occurring., Comment: 13 pages, 6 figures

Hyper- and hypothyroidism were induced by subcutaneous injection of thyroxine and by oral administration of methimazol in Brandt's voles. The effects of the two treatments on metabolic thermogenesis at 25°C and 4°C were investigated. The level of resting metabolic rate was closely related to thyroid status: high in the hyperthyroid case and low in the hypothyroid case. However, no increase in resting metabolic rate occurred in either case during further cold acclimation. Hyperthyroidism resulted in an increased nonshivering thermogenesis, which was much enhanced by lower temperature, but hypothyroidism led to a suppressed nonshivering thermogenesis in the cold. The state-4 and state-3 respirations and the activities of cytochrome-c oxidase of liver mitochondria were elevated in hyperthyroid animals but attenuated in hypothyroid ones. However, these levels were scarcely changed after further cold acclimation. Both hyperthyroidism and cold acclimation induced the recruitment of brown adipose tissue, but bro...