缺陷增加了建筑项目的成本和持续时间。自动缺陷检测将减少文档工作，这是降低延迟建筑项目的缺陷风险所必需的。由于混凝土是一种广泛使用的建筑材料，因此这项工作着重于检测蜂窝，这是混凝土结构的实质缺陷，甚至可能影响结构完整性。首先，比较图像是从网络上刮下来或从实际实践中获得的。结果表明，Web图像仅代表蜂窝的选择，并且不会捕获完整的差异。其次，对MASK R-CNN和EFIDENENET-B0进行了培训，用于评估实例分割和基于斑块的分类，分别达到47.7％的精度和34.2％的召回率以及68.5％的精度和55.7％的召回率。尽管这些模型的性能不足以完全自动化缺陷检测，但这些模型可用于积极学习中，集成到缺陷文档系统中。总之，CNN可以帮助检测混凝土中的蜂窝。

在这项工作中，我们提出了一种具有里程碑意义的检索方法，该方法利用了全球和本地功能。暹罗网络用于全球功能提取和度量学习，该网络对具有里程碑意义的搜索进行了初步排名。我们利用暹罗体系结构的提取特征图作为本地描述符，然后使用本地描述符之间的余弦相似性进一步完善搜索结果。我们对Google Landmark数据集进行了更深入的分析，该数据集用于评估，并增加数据集以处理各种类内差异。此外，我们进行了几项实验，以比较转移学习和度量学习的影响以及使用其他局部描述符的实验。我们表明，使用本地功能的重新排列可以改善搜索结果。我们认为，使用余弦相似性的拟议的本地特征提取是一种简单的方法，可以扩展到许多其他检索任务。

Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information about the objects, such as their spatial location, their visual properties and their relative relationships. We propose to do so by evaluating them in the context of visual reasoning, where multiple objects with complex relationships and different attributes are at play. More specifically, we introduce a protocol to evaluate visual representations for the task of Visual Question Answering. In order to decouple visual feature extraction from reasoning, we design a specific attention-based reasoning module which is trained on the frozen visual representations to be evaluated, in a spirit similar to standard feature evaluations relying on shallow networks. We compare two types of visual representations, densely extracted local features and object-centric ones, against the performances of a perfect image representation using ground truth. Our main findings are two-fold. First, despite excellent performances on classical proxy tasks, such representations fall short for solving complex reasoning problem. Second, object-centric features better preserve the critical information necessary to perform visual reasoning. In our proposed framework we show how to methodologically approach this evaluation.

Large language models (LLMs) have shown impressive results across a variety of tasks while requiring little or no direct supervision. Further, there is mounting evidence that LLMs may have potential in information-seeking scenarios. We believe the ability of an LLM to attribute the text that it generates is likely to be crucial for both system developers and users in this setting. We propose and study Attributed QA as a key first step in the development of attributed LLMs. We develop a reproducable evaluation framework for the task, using human annotations as a gold standard and a correlated automatic metric that we show is suitable for development settings. We describe and benchmark a broad set of architectures for the task. Our contributions give some concrete answers to two key questions (How to measure attribution?, and How well do current state-of-the-art methods perform on attribution?), and give some hints as to how to address a third key question (How to build LLMs with attribution?).

Mapping with uncertainty representation is required in many research domains, such as localization and sensor fusion. Although there are many uncertainty explorations in pose estimation of an ego-robot with map information, the quality of the reference maps is often neglected. To avoid the potential problems caused by the errors of maps and a lack of the uncertainty quantification, an adequate uncertainty measure for the maps is required. In this paper, uncertain building models with abstract map surface using Gaussian Process (GP) is proposed to measure the map uncertainty in a probabilistic way. To reduce the redundant computation for simple planar objects, extracted facets from a Gaussian Mixture Model (GMM) are combined with the implicit GP map while local GP-block techniques are used as well. The proposed method is evaluated on LiDAR point clouds of city buildings collected by a mobile mapping system. Compared to the performances of other methods such like Octomap, Gaussian Process Occupancy Map (GPOM) and Bayersian Generalized Kernel Inference (BGKOctomap), our method has achieved higher Precision-Recall AUC for evaluated buildings.

Underwater navigation presents several challenges, including unstructured unknown environments, lack of reliable localization systems (e.g., GPS), and poor visibility. Furthermore, good-quality obstacle detection sensors for underwater robots are scant and costly; and many sensors like RGB-D cameras and LiDAR only work in-air. To enable reliable mapless underwater navigation despite these challenges, we propose a low-cost end-to-end navigation system, based on a monocular camera and a fixed single-beam echo-sounder, that efficiently navigates an underwater robot to waypoints while avoiding nearby obstacles. Our proposed method is based on Proximal Policy Optimization (PPO), which takes as input current relative goal information, estimated depth images, echo-sounder readings, and previous executed actions, and outputs 3D robot actions in a normalized scale. End-to-end training was done in simulation, where we adopted domain randomization (varying underwater conditions and visibility) to learn a robust policy against noise and changes in visibility conditions. The experiments in simulation and real-world demonstrated that our proposed method is successful and resilient in navigating a low-cost underwater robot in unknown underwater environments. The implementation is made publicly available at https://github.com/dartmouthrobotics/deeprl-uw-robot-navigation.

The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated Learning with Formal Differential Privacy Guarantees"). In this case, a concrete bound on the error is very relevant to reduce the privacy parameter. The standard mechanism for continual counting is the binary mechanism. We present a novel mechanism and show that its mean squared error is both asymptotically optimal and a factor 10 smaller than the error of the binary mechanism. We also show that the constants in our analysis are almost tight by giving non-asymptotic lower and upper bounds that differ only in the constants of lower-order terms. Our algorithm is a matrix mechanism for the counting matrix and takes constant time per release. We also use our explicit factorization of the counting matrix to give an upper bound on the excess risk of the private learning algorithm of Denisov et al. (NeurIPS 2022). Our lower bound for any continual counting mechanism is the first tight lower bound on continual counting under approximate differential privacy. It is achieved using a new lower bound on a certain factorization norm, denoted by $\gamma_F(\cdot)$, in terms of the singular values of the matrix. In particular, we show that for any complex matrix, $A \in \mathbb{C}^{m \times n}$, \[ \gamma_F(A) \geq \frac{1}{\sqrt{m}}\|A\|_1, \] where $\|\cdot \|$ denotes the Schatten-1 norm. We believe this technique will be useful in proving lower bounds for a larger class of linear queries. To illustrate the power of this technique, we show the first lower bound on the mean squared error for answering parity queries.

Traffic state prediction in a transportation network is paramount for effective traffic operations and management, as well as informed user and system-level decision-making. However, long-term traffic prediction (beyond 30 minutes into the future) remains challenging in current research. In this work, we integrate the spatio-temporal dependencies in the transportation network from network modeling, together with the graph convolutional network (GCN) and graph attention network (GAT). To further tackle the dramatic computation and memory cost caused by the giant model size (i.e., number of weights) caused by multiple cascaded layers, we propose sparse training to mitigate the training cost, while preserving the prediction accuracy. It is a process of training using a fixed number of nonzero weights in each layer in each iteration. We consider the problem of long-term traffic speed forecasting for a real large-scale transportation network data from the California Department of Transportation (Caltrans) Performance Measurement System (PeMS). Experimental results show that the proposed GCN-STGT and GAT-STGT models achieve low prediction errors on short-, mid- and long-term prediction horizons, of 15, 30 and 45 minutes in duration, respectively. Using our sparse training, we could train from scratch with high sparsity (e.g., up to 90%), equivalent to 10 times floating point operations per second (FLOPs) reduction on computational cost using the same epochs as dense training, and arrive at a model with very small accuracy loss compared with the original dense training

神经网络作为快速物理模拟器具有许多工程设计任务的潜力。广泛应用程序的先决条件是易于使用的工作流程，用于在合理的时间内生成培训数据集，并且网络可以推广到看不见的系统的能力。与大多数以前的培训系统类似于评估数据集的工作相反，我们建议将培训系统的类型调整到网络体系结构中。具体而言，我们应用一个完全卷积的网络，因此设计了具有随机分配的物理属性的随机体素的3D系统。该想法已测试电子系统中的瞬时热扩散。仅在随机的“ Minecraft”系统上进行训练，我们获得了对电子系统的良好概括，这是训练系统的四倍（一步预测误差为0.07％，比0.8％）。

模拟虚拟人群的轨迹是计算机图形中通常遇到的任务。最近的一些作品应用了强化学习方法来使虚拟代理动画，但是在基本模拟设置方面，它们通常会做出不同的设计选择。这些选择中的每一个都有合理的使用依据，因此并不明显其真正的影响是什么，以及它们如何影响结果。在这项工作中，我们从对学习绩效的影响以及根据能源效率测得的模拟的质量分析了其中一些任意选择。我们对奖励函数设计的性质进行理论分析，并经验评估使用某些观察和动作空间对各种情况的影响，并将奖励函数和能量使用作为指标。我们表明，直接使用相邻代理的信息作为观察，通常优于更广泛使用的射线播放。同样，与具有绝对观察结果的自动对照相比，使用具有以自我为中心的观察的非体力学对照倾向于产生更有效的行为。这些选择中的每一个都对结果产生重大且潜在的非平凡影响，因此研究人员应该注意选择和报告他们的工作。