Search

With the rapid advancement of the Internet of Things (IoT) and Artificial Intelligence (AI), intelligent information services are being increasingly integrated across various sectors, including healthcare, industry, and transportation. Traditional solutions rely on centralized cloud processing, which encounters considerable challenges in fulfilling the Quality of Service (QoS) requirements of Computer Vision (CV) tasks generated in the resource-constrained infrastructure-less environments. In this paper, we introduce a distributed framework called CoUAV-Pro for multi-task video processing powered by Unmanned Aerial Vehicles (UAVs). This framework empowers multiple UAVs to meet the service demands of various computer vision (CV) tasks in infrastructure-less environments, thereby eliminating the need for centralized processing. Specifically, we develop a novel task allocation algorithm that leverages enhanced distributed actor-critic networks within CoUAV-Pro, aiming to optimize task processing efficiency while contending with constraints associated with UAV's energy, computational, and communication resources. Comprehensive experiments demonstrate that our proposed solution achieves satisfactory performance levels against those of centralized methods across key metrics including task acquisition rates, task latency, and energy consumption.

Unsupervised anomaly detection is a challenging computer vision task, in which 2D-based anomaly detection methods have been extensively studied. However, multimodal anomaly detection based on RGB images and 3D point clouds requires further investigation. The existing methods are mainly inspired by memory bank based methods commonly used in 2D-based anomaly detection, which may cost extra memory for storing mutimodal features. In present study, a novel memoryless method MDSS is proposed for multimodal anomaly detection, which employs a light-weighted student-teacher network and a signed distance function to learn from RGB images and 3D point clouds respectively, and complements the anomaly information from the two modalities. Specifically, a student-teacher network is trained with normal RGB images and masks generated from point clouds by a dynamic loss, and the anomaly score map could be obtained from the discrepancy between the output of student and teacher. Furthermore, the signed distance function learns from normal point clouds to predict the signed distances between points and surface, and the obtained signed distances are used to generate anomaly score map. Subsequently, the anomaly score maps are aligned to generate the final anomaly score map for detection. The experimental results indicate that MDSS is comparable but more stable than the SOTA memory bank based method Shape-guided, and furthermore performs better than other baseline methods., Comment: 14 pages, 4 figures, 2 tables, to be published in PRCV-2024

The intelligent reflection surface (IRS) and unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) system is widely used in temporary and emergency scenarios. Our goal is to minimize the energy consumption of the MEC system by jointly optimizing UAV locations, IRS phase shift, task offloading, and resource allocation with a variable number of UAVs. To this end, we propose a Flexible REsource Scheduling (FRES) framework by employing a novel deep progressive reinforcement learning which includes the following innovations: Firstly, a novel multi-task agent is presented to deal with the mixed integer nonlinear programming (MINLP) problem. The multi-task agent has two output heads designed for different tasks, in which a classified head is employed to make offloading decisions with integer variables while a fitting head is applied to solve resource allocation with continuous variables. Secondly, a progressive scheduler is introduced to adapt the agent to the varying number of UAVs by progressively adjusting a part of neurons in the agent. This structure can naturally accumulate experiences and be immune to catastrophic forgetting. Finally, a light taboo search (LTS) is introduced to enhance the global search of the FRES. The numerical results demonstrate the superiority of the FRES framework which can make real-time and optimal resource scheduling even in dynamic MEC systems., Comment: 13 pages, 10 figures

We investigate Riemannian manifolds $(M^n,g)$ whose curvature operator of the second kind $\mathring{R}$ satisfies the condition \begin{equation*} \alpha^{-1} (\lambda_1 +\cdots +\lambda_{\alpha}) > - \theta \bar{\lambda}, \end{equation*} where $\lambda_1 \leq \cdots \leq \lambda_{(n-1)(n+2)/2}$ are the eigenvalues of $\mathring{R}$, $\bar{\lambda}$ is their average, and $\theta > -1$. Under such conditions with optimal $\theta$ depending on $n$ and $\alpha$, we prove two differentiable sphere theorems in dimensions three and four, a homological sphere theorem in higher dimensions, and a curvature characterization of K\"ahler space forms. These results generalize recent works corresponding to $\theta =0$ of Cao-Gursky-Tran, Nienhaus-Petersen-Wink, and the author. Moreover, examples are provided to demonstrate the sharpness of all results., Comment: 28 pages; comments are welcome

In this paper, we propose an effective two-stage approach named Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts while achieving high fidelity by using a pre-trained multi-view diffusion model. Multi-view diffusion models, such as MVDream, have shown to generate high-fidelity 3D assets using score distillation sampling (SDS). However, applied naively, these methods often fail to comprehend compositional text prompts, and may often entirely omit certain subjects or parts. To address this issue, we first advocate leveraging text-guided 4-view images as the bottleneck in the text-to-3D pipeline. We then introduce an attention refocusing mechanism to encourage text-aligned 4-view image generation, without the necessity to re-train the multi-view diffusion model or craft a high-quality compositional 3D dataset. We further propose a hybrid optimization strategy to encourage synergy between the SDS loss and the sparse RGB reference images. Our method consistently outperforms previous state-of-the-art (SOTA) methods in generating compositional 3D assets, excelling in both quality and accuracy, and enabling diverse 3D from the same text prompt., Comment: 9 pages, 10 figures

We consider the concept of strong pluripotency of dynamical systems for a hyperbolic invariant set, as introduced in [KNS]. To the best of our knowledge, for the whole hyperbolic invariant set, the existence of robust strongly pluripotent dynamical systems has not been proven in previous studies. In fact, there is an example of strongly pluripotent dynamical systems in [CV01], but its robustness has not been proven. On the other hand, robust strongly pluripotent dynamical systems for some proper subsets of hyperbolic sets had been found in [KS17, KNS]. In this paper, we provide a combinatorial way to recognize strongly pluripotent diffeomorphisms in a Newhouse domain and prove that they are $C^r$-robust, $2\leq r< \infty$. More precisely, we prove that there is a 2-dimensional diffeomorphism with a wild Smale horseshoe which has a $C^r$ neighborhood $\mathcal{U}_0$ where all elements are strongly pluripotent for the whole Smale horseshoe. Moreover, it follows from the result that any property, such as having a non-trivial physical measure supported by the Smale horseshoe or having historic behavior, is $C^r$-persistent relative to a dense subset of $\mathcal{U}_0$., Comment: 39 pages, 11 figures

Neural Radiance Field (NeRF), as an implicit 3D scene representation, lacks inherent ability to accommodate changes made to the initial static scene. If objects are reconfigured, it is difficult to update the NeRF to reflect the new state of the scene without time-consuming data re-capturing and NeRF re-training. To address this limitation, we develop the first update method for NeRFs to physical changes. Our method takes only sparse new images (e.g. 4) of the altered scene as extra inputs and update the pre-trained NeRF in around 1 to 2 minutes. Particularly, we develop a pipeline to identify scene changes and update the NeRF accordingly. Our core idea is the use of a second helper NeRF to learn the local geometry and appearance changes, which sidesteps the optimization difficulties in direct NeRF fine-tuning. The interpolation power of the helper NeRF is the key to accurately reconstruct the un-occluded objects regions under sparse view supervision. Our method imposes no constraints on NeRF pre-training, and requires no extra user input or explicit semantic priors. It is an order of magnitude faster than re-training NeRF from scratch while maintaining on-par and even superior performance.

The development of generative models that create 3D content from a text prompt has made considerable strides thanks to the use of the score distillation sampling (SDS) method on pre-trained diffusion models for image generation. However, the SDS method is also the source of several artifacts, such as the Janus problem, the misalignment between the text prompt and the generated 3D model, and 3D model inaccuracies. While existing methods heavily rely on the qualitative assessment of these artifacts through visual inspection of a limited set of samples, in this work we propose more objective quantitative evaluation metrics, which we cross-validate via human ratings, and show analysis of the failure cases of the SDS technique. We demonstrate the effectiveness of this analysis by designing a novel computationally efficient baseline model that achieves state-of-the-art performance on the proposed metrics while addressing all the above-mentioned artifacts.

Due to their short timescale, stellar flares are a challenging target for the most modern synoptic sky surveys. The upcoming Vera C. Rubin Legacy Survey of Space and Time (LSST), a project designed to collect more data than any precursor survey, is unlikely to detect flares with more than one data point in its main survey. We developed a methodology to enable LSST studies of stellar flares, with a focus on flare temperature and temperature evolution, which remain poorly constrained compared to flare morphology. By leveraging the sensitivity expected from the Rubin system, Differential Chromatic Refraction can be used to constrain flare temperature from a single-epoch detection, which will enable statistical studies of flare temperatures and constrain models of the physical processes behind flare emission using the unprecedentedly high volume of data produced by Rubin over the 10-year LSST. We model the refraction effect as a function of the atmospheric column density, photometric filter, and temperature of the flare, and show that flare temperatures at or above ~4,000K can be constrained by a single g-band observation at airmass X > 1.2, given the minimum specified requirement on single-visit relative astrometric accuracy of LSST, and that a surprisingly large number of LSST observations is in fact likely be conducted at X > 1.2, in spite of image quality requirements pushing the survey to preferentially low X. Having failed to measure flare DCR in LSST precursor surveys, we make recommendations on survey design and data products that enable these studies in LSST and other future surveys., Comment: 18 pages, 16 figures, 1 table. Submitted to the Astrophysical Journal Supplement Series

Charge density wave (CDW) is a collective quantum phenomenon with a charge modulation in solids1-2. Condensation of electron and hole pairs with finite momentum will lead to such an ordered state3-7. However, lattice symmetry breaking manifested as the softening of phonon modes can occur simultaneously, which makes it difficult to disentangle the origin of the transition8-14. Here, we report a condensed phase in low dimensional HfTe2, whereas angle-resolved photoemission spectroscopy (ARPES) measurements show a metal-insulator transition by lowering the temperature in single triatomic layer (TL) HfTe2. A full gap opening, renormalization of the bands, and emergence of replica bands at the M point are observed in the low temperatures, indicating formation of a CDW in the ground state.Raman spectroscopy shows no sign of lattice distortion within the detection limit. The results are corroborated by first-principles calculations, demonstrating the electronic origin of the CDW. By adding more layers, the phase transition is suppressed and completely destroyed at 3 TL because of the increased screening around the Fermi surface. Interestingly, a small amount of electron doping in 1 TL film during the growth significantly raises the transition temperature (TC), which is attributed to a reduced screening effect and a more balanced electron and hole carrier density. Our results indicate a CDW formation mechanism consistent with the excitonic insulator phase in low dimensional HfTe2 and open up opportunity for realization of novel quantum states based on exciton condensation., Comment: https://www.nature.com/articles/s41567-023-02349-0 published in Nature Physics

The purpose of remote sensing image change detection (RSCD) is to detect differences between bi-temporal images taken at the same place. Deep learning has been extensively used to RSCD tasks, yielding significant results in terms of result recognition. However, due to the shooting angle of the satellite, the impacts of thin clouds, and certain lighting conditions, the problem of fuzzy edges in the change region in some remote sensing photographs cannot be properly handled using current RSCD algorithms. To solve this issue, we proposed a Body Decouple Multi-Scale by fearure Aggregation change detection (BD-MSA), a novel model that collects both global and local feature map information in the channel and space dimensions of the feature map during the training and prediction phases. This approach allows us to successfully extract the change region's boundary information while also divorcing the change region's main body from its boundary. Numerous studies have shown that the assessment metrics and evaluation effects of the model described in this paper on the publicly available datasets DSIFN-CD, S2Looking and WHU-CD are the best when compared to other models.

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However, continuously updating LLMs for alignment raises a distribution gap between model-generated samples and human-annotated responses, hindering training effectiveness. To mitigate this issue, previous methods require additional preference annotation on newly generated samples to adapt to the shifted distribution, which consumes a large amount of annotation resources. Targeting more efficient human preference optimization, we propose an Adversarial Preference Optimization (APO) framework, in which the LLM and the reward model update alternatively via a min-max game. Through adversarial training, the reward model can adapt to the shifted generation distribution of the LLM without any additional annotation. With comprehensive experiments, we find the proposed adversarial training framework further enhances existing alignment baselines in terms of LLM helpfulness and harmlessness. The code is at https://github.com/Linear95/APO., Comment: Accepted by ACL2024 findings

Deep learning accelerators address the computational demands of Deep Neural Networks (DNNs), departing from the traditional Von Neumann execution model. They leverage specialized hardware to align with the application domain's structure. Compilers for these accelerators face distinct challenges compared to those for general-purpose processors. These challenges include exposing and managing more micro-architectural features, handling software-managed scratch pads for on-chip storage, explicitly managing data movement, and matching DNN layers with varying hardware capabilities. These complexities necessitate a new approach to compiler design, as traditional compilers mainly focused on generating fine-grained instruction sequences while abstracting micro-architecture details. This paper introduces the Architecture Covenant Graph (ACG), an abstract representation of an architectural structure's components and their programmable capabilities. By enabling the compiler to work with the ACG, it allows for adaptable compilation workflows when making changes to accelerator design, reducing the need for a complete compiler redevelopment. Codelets, which express DNN operation functionality and evolve into execution mappings on the ACG, are key to this process. The Covenant compiler efficiently targets diverse deep learning accelerators, achieving 93.8% performance compared to state-of-the-art, hand-tuned DNN layer implementations when compiling 14 DNN layers from various models on two different architectures.

Intent detection and identification from multi-turn dialogue has become a widely explored technique in conversational agents, for example, voice assistants and intelligent customer services. The conventional approaches typically cast the intent mining process as a classification task. Although neural classifiers have proven adept at such classification tasks, the issue of neural network models often impedes their practical deployment in real-world settings. We present a novel graph-based multi-turn dialogue system called , which identifies a user's intent by identifying intent elements and a standard query from a dynamically constructed and extensible intent graph using reinforcement learning. In addition, we provide visualization components to monitor the immediate reasoning path for each turn of a dialogue, which greatly facilitates further improvement of the system., Comment: 4pages, 5 figures

Light echoes give us a unique perspective on the nature of supernovae and non-terminal stellar explosions. Spectroscopy of light echoes can reveal details on the kinematics of the ejecta, probe asymmetry, and reveal details on its interaction with circumstellar matter, thus expanding our understanding of these transient events. However, the spectral features arise from a complex interplay between the source photons, the reflecting dust geometry, and the instrumental setup and observing conditions. In this work we present an improved method for modeling these effects in light echo spectra, one that relaxes the simplifying assumption of a light curve weighted sum, and instead estimates the true relative contribution of each phase. We discuss our logic, the gains we obtain over light echo analysis method(s) used in the past, and prospects for further improvements. Lastly, we show how the new method improves our analysis of echoes from Tycho's supernova (SN 1572) as an example.

In this paper, we study the problem of end-to-end multi-person pose estimation. State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e.g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR. We present a simple yet effective transformer approach, named Group Pose. We simply regard $K$-keypoint pose estimation as predicting a set of $N\times K$ keypoint positions, each from a keypoint query, as well as representing each pose with an instance query for scoring $N$ pose predictions. Motivated by the intuition that the interaction, among across-instance queries of different types, is not directly helpful, we make a simple modification to decoder self-attention. We replace single self-attention over all the $N\times(K+1)$ queries with two subsequent group self-attentions: (i) $N$ within-instance self-attention, with each over $K$ keypoint queries and one instance query, and (ii) $(K+1)$ same-type across-instance self-attention, each over $N$ queries of the same type. The resulting decoder removes the interaction among across-instance type-different queries, easing the optimization and thus improving the performance. Experimental results on MS COCO and CrowdPose show that our approach without human box supervision is superior to previous methods with complex decoders, and even is slightly better than ED-Pose that uses human box supervision. $\href{https://github.com/Michel-liu/GroupPose-Paddle}{\rm Paddle}$ and $\href{https://github.com/Michel-liu/GroupPose}{\rm PyTorch}$ code are available., Comment: Accepted by ICCV 2023

We prove matrix Li-Yau-Hamilton estimates for positive solutions to the heat equation and the backward conjugate heat equation, both coupled with the K\"ahler-Ricci flow. As an application, we obtain a monotonicity formula., Comment: 13 pages. Comments are welcome