Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training data for free and significantly boosts the segmentation performance, especially for rare object categories. Although diverse, high-quality object instances used in Copy-Paste result in more performance gain, previous works utilize object instances either from human-annotated instance segmentation datasets or rendered from 3D object models, and both approaches are too expensive to scale up to obtain good diversity. In this paper, we revisit Copy-Paste at scale with the power of newly emerged zero-shot recognition models (e.g., CLIP) and text2image models (e.g., StableDiffusion). We demonstrate for the first time that using a text2image model to generate images or zero-shot recognition model to filter noisily crawled images for different object categories is a feasible way to make Copy-Paste truly scalable. To make such success happen, we design a data acquisition and processing framework, dubbed "X-Paste", upon which a systematic study is conducted. On the LVIS dataset, X-Paste provides impressive improvements over the strong baseline CenterNet2 with Swin-L as the backbone. Specifically, it archives +2.6 box AP and +2.1 mask AP gains on all classes and even more significant gains with +6.8 box AP +6.5 mask AP on long-tail classes.

With the booming deployment of Internet of Things, health monitoring applications have gradually prospered. Within the recent COVID-19 pandemic situation, interest in permanent remote health monitoring solutions has raised, targeting to reduce contact and preserve the limited medical resources. Among the technological methods to realize efficient remote health monitoring, federated learning (FL) has drawn particular attention due to its robustness in preserving data privacy. However, FL can yield to high communication costs, due to frequent transmissions between the FL server and clients. To tackle this problem, we propose in this paper a communication-efficient federated learning (CEFL) framework that involves clients clustering and transfer learning. First, we propose to group clients through the calculation of similarity factors, based on the neural networks characteristics. Then, a representative client in each cluster is selected to be the leader of the cluster. Differently from the conventional FL, our method performs FL training only among the cluster leaders. Subsequently, transfer learning is adopted by the leader to update its cluster members with the trained FL model. Finally, each member fine-tunes the received model with its own data. To further reduce the communication costs, we opt for a partial-layer FL aggregation approach. This method suggests partially updating the neural network model rather than fully. Through experiments, we show that CEFL can save up to to 98.45% in communication costs while conceding less than 3% in accuracy loss, when compared to the conventional FL. Finally, CEFL demonstrates a high accuracy for clients with small or unbalanced datasets.

部分微分方程（PDES）在科学和工程的许多学科中都是普遍的，难以解决。通常，PDE的闭合形式溶液不可用，数值近似方法是计算昂贵的。 PDE的参数在许多应用中是可变的，例如逆问题，控制和优化，风险评估和不确定性量化。在这些应用程序中，我们的目标是解决参数PDE而不是其中一个实例。我们所提出的方法，称为元 - 自动解码器（MAD），将参数PDES作为元学习问题求解，并利用\ Cite {Park2019DeepsDF}中的自动解码器结构来处理不同的任务/ PDE。从PDE管理方程和边界条件诱导的物理知识损失被用作不同任务的培训损失。疯狂的目标是学习一个良好的模型初始化，可以概括不同的任务，最终使未能学习的任务能够更快地学习。疯狂的灵感来自于（猜想）参数PDE解决方案的低维结构，并从流形学习的角度解释了我们的方法。最后，我们展示了疯狂的力量，虽然广泛的数值研究，包括汉堡等式，拉普尔斯方程和时域麦克斯韦方程。与其他深度学习方法相比，MAD表现出更快的收敛速度而不会失去准确性。

近年来，深入学习技术已被用来解决部分微分方程（PDE），其中物理信息的神经网络（PINNS）出现是解决前向和反向PDE问题的有希望的方法。具有点源的PDE，其表示为管理方程中的DIRAC DELTA函数是许多物理过程的数学模型。然而，由于DIRAC DELTA功能所带来的奇点，它们不能直接通过传统的PINNS方法来解决。我们提出了一种普遍的解决方案，以用三种新颖的技术解决这个问题。首先，DIRAC DELTA功能被建模为连续概率密度函数以消除奇点;其次，提出了下限约束的不确定性加权算法，以平衡点源区和其他区域之间的Pinns损失;第三，使用具有周期性激活功能的多尺度深度神经网络来提高PinnS方法的准确性和收敛速度。我们评估了三种代表性PDE的提出方法，实验结果表明，我们的方法优于基于深度学习的方法，涉及准确性，效率和多功能性。

Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationally expensive. Therefore, it is difficult to deploy them onto edge devices with scarce computational resources, e.g., mobile phones and wearable smart devices. Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i.e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i.e., the teacher GNN model). Nevertheless, most existing GNN-based KD methods lack fairness consideration. As a consequence, the student model usually inherits and even exaggerates the bias from the teacher GNN. To handle such a problem, we take initial steps towards fair knowledge distillation for GNNs. Specifically, we first formulate a novel problem of fair knowledge distillation for GNN-based teacher-student frameworks. Then we propose a principled framework named RELIANT to mitigate the bias exhibited by the student model. Notably, the design of RELIANT is decoupled from any specific teacher and student model structures, and thus can be easily adapted to various GNN-based KD frameworks. We perform extensive experiments on multiple real-world datasets, which corroborates that RELIANT achieves less biased GNN knowledge distillation while maintaining high prediction utility.

A further understanding of cause and effect within observational data is critical across many domains, such as economics, health care, public policy, web mining, online advertising, and marketing campaigns. Although significant advances have been made to overcome the challenges in causal effect estimation with observational data, such as missing counterfactual outcomes and selection bias between treatment and control groups, the existing methods mainly focus on source-specific and stationary observational data. Such learning strategies assume that all observational data are already available during the training phase and from only one source. This practical concern of accessibility is ubiquitous in various academic and industrial applications. That's what it boiled down to: in the era of big data, we face new challenges in causal inference with observational data, i.e., the extensibility for incrementally available observational data, the adaptability for extra domain adaptation problem except for the imbalance between treatment and control groups, and the accessibility for an enormous amount of data. In this position paper, we formally define the problem of continual treatment effect estimation, describe its research challenges, and then present possible solutions to this problem. Moreover, we will discuss future research directions on this topic.

Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot, generalized zero-shot and open set recognition using a unified framework. Specifically, we propose a weighted maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms. Distance constraints ensure that labeled samples are projected closer to their correct prototypes, in the embedding space, than to others. We illustrate that resulting model shows improvements in supervised, zero-shot, generalized zero-shot, and large open set recognition, with up to 310K class vocabulary on Animal with Attributes and ImageNet datasets.

Advances in computer vision and machine learning techniques have led to significant development in 2D and 3D human pose estimation from RGB cameras, LiDAR, and radars. However, human pose estimation from images is adversely affected by occlusion and lighting, which are common in many scenarios of interest. Radar and LiDAR technologies, on the other hand, need specialized hardware that is expensive and power-intensive. Furthermore, placing these sensors in non-public areas raises significant privacy concerns. To address these limitations, recent research has explored the use of WiFi antennas (1D sensors) for body segmentation and key-point body detection. This paper further expands on the use of the WiFi signal in combination with deep learning architectures, commonly used in computer vision, to estimate dense human pose correspondence. We developed a deep neural network that maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions. The results of the study reveal that our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches, by utilizing WiFi signals as the only input. This paves the way for low-cost, broadly accessible, and privacy-preserving algorithms for human sensing.

With the increasing ability of large language models (LLMs), in-context learning (ICL) has become a new paradigm for natural language processing (NLP), where LLMs make predictions only based on contexts augmented with a few training examples. It has been a new trend exploring ICL to evaluate and extrapolate the ability of LLMs. In this paper, we aim to survey and summarize the progress, challenges, and future work in ICL. We first present a formal definition of ICL and clarify its correlation to related studies. Then, we organize and discuss advanced techniques of ICL, including training strategies, prompting strategies, and so on. Finally, we present the challenges of ICL and provide potential directions for further research. We hope our work can encourage more research on uncovering how ICL works and improving ICL in future work.

Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work focuses on the former. Previous methods build the network with several modules like CNN, LSTM and Attention. Recent methods combine the Transformer with these modules for better performance. However, it requires tedious optimization skills to train a network composed of mixed modules, making these methods inconvenient to be used in practice. In this paper, we propose to design \emph{pure Transformer-based networks} for deep RL, aiming at providing off-the-shelf backbones for both the online and offline settings. Specifically, the Transformer in Transformer (TIT) backbone is proposed, which cascades two Transformers in a very natural way: the inner one is used to process a single observation, while the outer one is responsible for processing the observation history; combining both is expected to extract spatial-temporal representations for good decision-making. Experiments show that TIT can achieve satisfactory performance in different settings, consistently.