For time-critical IoT applications using deep learning, inference acceleration through distributed computing is a promising approach to meet a stringent deadline. In this paper, we implement a working prototype of a new distributed inference acceleration method HALP using three raspberry Pi 4. HALP accelerates inference by designing a seamless collaboration among edge devices (EDs) in Edge Computing. We maximize the parallelization between communication and computation among the collaborative EDs by optimizing the task partitioning ratio based on the segment-based partitioning. Experimental results show that the distributed inference HALP achieves 1.7x inference acceleration for VGG-16. Then, we combine distributed inference with conventional neural network model compression by setting up different shrinking hyperparameters for MobileNet-V1. In this way, we can further accelerate inference but at the cost of inference accuracy loss. To strike a balance between latency and accuracy, we propose dynamic model selection to select a model which provides the highest accuracy within the latency constraint. It is shown that the model selection with distributed inference HALP can significantly improve service reliability compared to the conventional stand-alone computation.

由少量镜头组成的全景环形镜头（PAL）在全景周围具有巨大潜力，该镜头围绕着移动和可穿戴设备的传感任务，因为其尺寸很小，并且视野很大（FOV）。然而，由于缺乏畸变校正的镜头，小体积PAL的图像质量仅限于光学极限。在本文中，我们提出了一个环形计算成像（ACI）框架，以打破轻质PAL设计的光学限制。为了促进基于学习的图像恢复，我们引入了基于波浪的模拟管道，用于全景成像，并通过多个数据分布来应对合成间隙。提出的管道可以轻松地适应具有设计参数的任何PAL，并且适用于宽松的设计。此外，我们考虑了全景成像和物理知识学习的物理先验，我们设计了物理知情的图像恢复网络（PI2RNET）。在数据集级别，我们创建了Divpano数据集，其广泛的实验表明，我们提出的网络在空间变化的降级下在全景图像恢复中设置了新的最新技术。此外，对只有3个球形镜头的简单PAL上提议的ACI的评估揭示了高质量全景成像与紧凑设计之间的微妙平衡。据我们所知，我们是第一个探索PAL中计算成像（CI）的人。代码和数据集将在https://github.com/zju-jiangqi/aci-pi2rnet上公开提供。

特征交互已被识别为机器学习中的一个重要问题，这对于点击率（CTR）预测任务也是非常重要的。近年来，深度神经网络（DNN）可以自动从原始稀疏功能中学习隐式非线性交互，因此已广泛用于工业CTR预测任务。然而，在DNN中学到的隐式特征交互不能完全保留原始和经验特征交互的完整表示容量（例如，笛卡尔产品）而不会损失。例如，简单地尝试学习特征A和特征B <A，B>作为新特征的显式笛卡尔产品表示可以胜过先前隐式功能交互模型，包括基于分解机（FM）的模型及其变体。在本文中，我们提出了一个共同行动网络（CAN），以近似于显式成对特征交互，而不会引入太多的附加参数。更具体地，给出特征A及其相关的特征B，通过学习两组参数来建模它们的特征交互：1）嵌入特征A和2）以表示特征B的多层Perceptron（MLP）。近似通过通过特征B的MLP网络传递特征A的嵌入可以获得特征交互。我们将这种成对特征交互作为特征合作，并且这种共动网单元可以提供拟合复合物的非常强大的容量功能交互。公共和工业数据集的实验结果表明，可以优于最先进的CTR模型和笛卡尔产品方法。此外，可以在阿里巴巴的显示广告系统中部署，获得12 \％的CTR和8 \％关于每个Mille（RPM）的收入，这是对业务的巨大改进。

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 recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.

The surrogate loss of variational autoencoders (VAEs) poses various challenges to their training, inducing the imbalance between task fitting and representation inference. To avert this, the existing strategies for VAEs focus on adjusting the tradeoff by introducing hyperparameters, deriving a tighter bound under some mild assumptions, or decomposing the loss components per certain neural settings. VAEs still suffer from uncertain tradeoff learning.We propose a novel evolutionary variational autoencoder (eVAE) building on the variational information bottleneck (VIB) theory and integrative evolutionary neural learning. eVAE integrates a variational genetic algorithm into VAE with variational evolutionary operators including variational mutation, crossover, and evolution. Its inner-outer-joint training mechanism synergistically and dynamically generates and updates the uncertain tradeoff learning in the evidence lower bound (ELBO) without additional constraints. Apart from learning a lossy compression and representation of data under the VIB assumption, eVAE presents an evolutionary paradigm to tune critical factors of VAEs and deep neural networks and addresses the premature convergence and random search problem by integrating evolutionary optimization into deep learning. Experiments show that eVAE addresses the KL-vanishing problem for text generation with low reconstruction loss, generates all disentangled factors with sharp images, and improves the image generation quality,respectively. eVAE achieves better reconstruction loss, disentanglement, and generation-inference balance than its competitors.

Surgical robot automation has attracted increasing research interest over the past decade, expecting its huge potential to benefit surgeons, nurses and patients. Recently, the learning paradigm of embodied AI has demonstrated promising ability to learn good control policies for various complex tasks, where embodied AI simulators play an essential role to facilitate relevant researchers. However, existing open-sourced simulators for surgical robot are still not sufficiently supporting human interactions through physical input devices, which further limits effective investigations on how human demonstrations would affect policy learning. In this paper, we study human-in-the-loop embodied intelligence with a new interactive simulation platform for surgical robot learning. Specifically, we establish our platform based on our previously released SurRoL simulator with several new features co-developed to allow high-quality human interaction via an input device. With these, we further propose to collect human demonstrations and imitate the action patterns to achieve more effective policy learning. We showcase the improvement of our simulation environment with the designed new features and tasks, and validate state-of-the-art reinforcement learning algorithms using the interactive environment. Promising results are obtained, with which we hope to pave the way for future research on surgical embodied intelligence. Our platform is released and will be continuously updated in the website: https://med-air.github.io/SurRoL/

Brain midline shift (MLS) is one of the most critical factors to be considered for clinical diagnosis and treatment decision-making for intracranial hemorrhage. Existing computational methods on MLS quantification not only require intensive labeling in millimeter-level measurement but also suffer from poor performance due to their dependence on specific landmarks or simplified anatomical assumptions. In this paper, we propose a novel semi-supervised framework to accurately measure the scale of MLS from head CT scans. We formulate the MLS measurement task as a deformation estimation problem and solve it using a few MLS slices with sparse labels. Meanwhile, with the help of diffusion models, we are able to use a great number of unlabeled MLS data and 2793 non-MLS cases for representation learning and regularization. The extracted representation reflects how the image is different from a non-MLS image and regularization serves an important role in the sparse-to-dense refinement of the deformation field. Our experiment on a real clinical brain hemorrhage dataset has achieved state-of-the-art performance and can generate interpretable deformation fields.

Audio-Visual scene understanding is a challenging problem due to the unstructured spatial-temporal relations that exist in the audio signals and spatial layouts of different objects and various texture patterns in the visual images. Recently, many studies have focused on abstracting features from convolutional neural networks while the learning of explicit semantically relevant frames of sound signals and visual images has been overlooked. To this end, we present an end-to-end framework, namely attentional graph convolutional network (AGCN), for structure-aware audio-visual scene representation. First, the spectrogram of sound and input image is processed by a backbone network for feature extraction. Then, to build multi-scale hierarchical information of input features, we utilize an attention fusion mechanism to aggregate features from multiple layers of the backbone network. Notably, to well represent the salient regions and contextual information of audio-visual inputs, the salient acoustic graph (SAG) and contextual acoustic graph (CAG), salient visual graph (SVG), and contextual visual graph (CVG) are constructed for the audio-visual scene representation. Finally, the constructed graphs pass through a graph convolutional network for structure-aware audio-visual scene recognition. Extensive experimental results on the audio, visual and audio-visual scene recognition datasets show that promising results have been achieved by the AGCN methods. Visualizing graphs on the spectrograms and images have been presented to show the effectiveness of proposed CAG/SAG and CVG/SVG that could focus on the salient and semantic relevant regions.