对比性语言图像预训练（剪辑）已被证明可以学习具有出色传递性的视觉表示，从而实现了零击分类的有希望的准确性。为了进一步提高其下游性能，现有作品在剪辑上提出了其他可学习的模块，并通过几次训练集对其进行微调。但是，由此产生的额外培训成本和数据要求严重阻碍了模型部署和知识转移的效率。在本文中，我们引入了一种自由午餐的增强方法CALIP，以通过无参数注意模块来提高Clip的零拍摄性能。具体而言，我们指导视觉和文本表示相互交互，并通过注意探索跨模式的信息特征。由于预训练大大降低了两种方式之间的嵌入距离，因此我们在注意力中丢弃所有可学习的参数，并在双向更新多模式特征，从而使整个过程无参数且无培训。通过这种方式，图像与文本感知信号混合在一起，文本表示形式被视觉引导以获得更好的自适应零射击对齐。我们在14个数据集的各种基准上评估CALIP，用于2D图像和3D Point Cloud几乎没有分类，显示出一致的零弹性性能改进了夹子。基于此，我们进一步在Calip的注意模块中插入了少量线性层，并在少量射击设置下验证我们的鲁棒性，与现有方法相比，这也可以实现领先的性能。这些广泛的实验证明了我们的方法在有效增强夹子方面的优势。

垂直联合学习（VFL）是一个新兴的范式，允许不同的方（例如组织或企业）协作建立具有隐私保护的机器学习模型。在训练阶段，VFL仅交换跨各方的中间统计数据，即正向激活和向后导数，以计算模型梯度。然而，由于其地理分布性质，VFL训练通常会受到低WAN带宽的影响。在本文中，我们介绍了一种新颖有效的VFL培训框架Celu-VFL，该框架利用了本地更新技术来减少跨党的交流回合。 CELU-VFL缓存了陈旧的统计数据，并将其重新估算模型梯度，而无需交换临时统计。提出了重要的技术来提高收敛性能。首先，为了解决随机方差问题，我们提出了一种统一的采样策略，以公平地选择本地更新的陈旧统计信息。其次，为了利用稳定性带来的错误，我们设计了一种实例加权机制，以衡量估计梯度的可靠性。理论分析证明，CELU-VFL达到了与Vanilla VFL训练相似的亚线性收敛率，但需要更少的通信回合。公共和现实世界工作负载的经验结果验证了CELU-VFL的速度可能比现有作品快六倍。

专家混合物（MOE）由于其成功提高了模型质量，特别是在变压器方面的成功而变得流行。通过向几个专家提供稀疏门的令牌，每个专家只包含完整模型的一部分，Moe将模型尺寸保持不变，并且显着降低了每次标记计算，从而有效地缩放神经网络。但是，我们发现，目前的联合训练专家和稀疏门的方法引入了对模型精度的负面影响，缩短了昂贵的大规模模型训练的效率。在这项工作中，我们提出了用于MOE训练的密集至稀疏的门（DTS-Gate）。具体而言，代替使用永久稀疏门，DTS-Gate开始作为向所有专家路由令牌的密集栅极开始，然后逐渐和自适应地成为稀疏，而路线较少到更少的专家。与DTS-Gate的Moe自然地通过培训所有专家训练专家和稀疏门的训练，然后学习稀疏门。实验表明，与GPT-MOE（1.5B）模型中的最先进的开关门相比，使用OpenWeBtext数据集（40GB），DTS-Gate可以获得2.0倍的加速以达到相同的验证困惑，如以及更高的拖鞋 - 效率为1.42倍的加速。

嵌入式模型是高维数据的有效学习范例。但是，嵌入模型的一个开放问题是它们的表示（潜在因子）通常会导致大参数空间。我们观察到，现有的分布式训练框架面临嵌入模型的可伸缩性问题，因为从服务器的共享嵌入参数更新和检索共享嵌入参数通常占主导地位培训周期。在本文中，我们提出了一种新的系统框架，可显着提高巨大嵌入模型培训的可扩展性。我们拥抱嵌入的嵌入式作为绩效机会的倾斜流行分布，并利用它来解决具有嵌入缓存的通信瓶颈。为确保缓存跨越一致性，我们将新的一致性模型纳入HET设计，该模型提供了在每嵌入的基础上提供细粒度的一致性保证。与以前的工作相比，只允许读取操作的僵化，HET也利用了写入操作的血液性。六种代表性任务的评估表明，在最先进的基线上，HET达到高达88％的嵌入通信减少和高达20.68倍的性能加速。

最近，通过对比视觉 - 语言预训练（CLIP）的零射击和少量学习已经在2D视觉识别上显示了鼓舞人心的性能，从而了解在开放词汇设置中将图像与其相应的文本匹配。然而，它仍然在探索中，是否通过2D中的大规模图像文本对预先训练的剪辑可以推广到3D识别。在本文中，我们通过提出引人点来识别这种设置是可行的，这在剪辑编码点云和3D类别文本之间进行对准。具体地，我们通过将点云投射到多视图深度映射而不呈现，并聚合视图零拍摄预测以实现从2D到3D的知识转移。首先，我们设计了一个视图间适配器，以更好地提取全局特征，并自适应地融合从3D到2D预培训的剪辑中学到的几次拍摄知识。只需在几次拍摄设置中微调轻量级适配器，可以在很大程度上提高要素的性能。此外，我们遵守CONTCLIP和古典3D监督网络之间的互补财产。通过简单的合奏，PointClip提高了基线的性能，甚至超越了最先进的模型。因此，PointClip是在低资源成本和数据制度下通过剪辑的有效3D点云理解的有希望的替代方案。我们在广泛采用的ModelNet10，ModelNet40和挑战ScanObjectnn上进行彻底的实验，以证明Pointclip的有效性。代码在https://github.com/zrrskywalker/pointclip发布。

Consensus clustering aggregates partitions in order to find a better fit by reconciling clustering results from different sources/executions. In practice, there exist noise and outliers in clustering task, which, however, may significantly degrade the performance. To address this issue, we propose a novel algorithm -- robust consensus clustering that can find common ground truth among experts' opinions, which tends to be minimally affected by the bias caused by the outliers. In particular, we formalize the robust consensus clustering problem as a constraint optimization problem, and then derive an effective algorithm upon alternating direction method of multipliers (ADMM) with rigorous convergence guarantee. Our method outperforms the baselines on benchmarks. We apply the proposed method to the real-world advertising campaign segmentation and forecasting tasks using the proposed consensus clustering results based on the similarity computed via Kolmogorov-Smirnov Statistics. The accurate clustering result is helpful for building the advertiser profiles so as to perform the forecasting.

Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no matter whether there exist objects or not. This paradigm, although effective, is inefficient because the detectors have to go through all patches, severely hindering the inference speed. This paper presents an Objectness Activation Network (OAN) to help detectors focus on fewer patches but achieve more efficient inference and more accurate results, enabling a simple and effective solution to object detection in large images. In brief, OAN is a light fully-convolutional network for judging whether each patch contains objects or not, which can be easily integrated into many object detectors and jointly trained with them end-to-end. We extensively evaluate our OAN with five advanced detectors. Using OAN, all five detectors acquire more than 30.0% speed-up on three large-scale aerial image datasets, meanwhile with consistent accuracy improvements. On extremely large Gaofen-2 images (29200$\times$27620 pixels), our OAN improves the detection speed by 70.5%. Moreover, we extend our OAN to driving-scene object detection and 4K video object detection, boosting the detection speed by 112.1% and 75.0%, respectively, without sacrificing the accuracy. Code is available at https://github.com/Ranchosky/OAN.

Due to the issue that existing wireless sensor network (WSN)-based anomaly detection methods only consider and analyze temporal features, in this paper, a self-supervised learning-based anomaly node detection method based on an autoencoder is designed. This method integrates temporal WSN data flow feature extraction, spatial position feature extraction and intermodal WSN correlation feature extraction into the design of the autoencoder to make full use of the spatial and temporal information of the WSN for anomaly detection. First, a fully connected network is used to extract the temporal features of nodes by considering a single mode from a local spatial perspective. Second, a graph neural network (GNN) is used to introduce the WSN topology from a global spatial perspective for anomaly detection and extract the spatial and temporal features of the data flows of nodes and their neighbors by considering a single mode. Then, the adaptive fusion method involving weighted summation is used to extract the relevant features between different models. In addition, this paper introduces a gated recurrent unit (GRU) to solve the long-term dependence problem of the time dimension. Eventually, the reconstructed output of the decoder and the hidden layer representation of the autoencoder are fed into a fully connected network to calculate the anomaly probability of the current system. Since the spatial feature extraction operation is advanced, the designed method can be applied to the task of large-scale network anomaly detection by adding a clustering operation. Experiments show that the designed method outperforms the baselines, and the F1 score reaches 90.6%, which is 5.2% higher than those of the existing anomaly detection methods based on unsupervised reconstruction and prediction. Code and model are available at https://github.com/GuetYe/anomaly_detection/GLSL

We study algorithms for detecting and including glass objects in an optimization-based Simultaneous Localization and Mapping (SLAM) algorithm in this work. When LiDAR data is the primary exteroceptive sensory input, glass objects are not correctly registered. This occurs as the incident light primarily passes through the glass objects or reflects away from the source, resulting in inaccurate range measurements for glass surfaces. Consequently, the localization and mapping performance is impacted, thereby rendering navigation in such environments unreliable. Optimization-based SLAM solutions, which are also referred to as Graph SLAM, are widely regarded as state of the art. In this paper, we utilize a simple and computationally inexpensive glass detection scheme for detecting glass objects and present the methodology to incorporate the identified objects into the occupancy grid maintained by such an algorithm (Google Cartographer). We develop both local (submap level) and global algorithms for achieving the objective mentioned above and compare the maps produced by our method with those produced by an existing algorithm that utilizes particle filter based SLAM.

Persuasion modeling is a key building block for conversational agents. Existing works in this direction are limited to analyzing textual dialogue corpus. We argue that visual signals also play an important role in understanding human persuasive behaviors. In this paper, we introduce the first multimodal dataset for modeling persuasion behaviors. Our dataset includes 199 dialogue transcriptions and videos captured in a multi-player social deduction game setting, 26,647 utterance level annotations of persuasion strategy, and game level annotations of deduction game outcomes. We provide extensive experiments to show how dialogue context and visual signals benefit persuasion strategy prediction. We also explore the generalization ability of language models for persuasion modeling and the role of persuasion strategies in predicting social deduction game outcomes. Our dataset, code, and models can be found at https://persuasion-deductiongame.socialai-data.org.