Transformers are becoming increasingly popular due to their superior performance over conventional convolutional neural networks(CNNs). However, transformers usually require a much larger amount of memory to train than CNNs, which prevents their application in many low resource settings. Local learning, which divides the network into several distinct modules and trains them individually, is a promising alternative to the end-to-end (E2E) training approach to reduce the amount of memory for training and to increase parallelism. This paper is the first to apply Local Learning on transformers for this purpose. The standard CNN-based local learning method, InfoPro [32], reconstructs the input images for each module in a CNN. However, reconstructing the entire image does not generalize well. In this paper, we propose a new mechanism for each local module, where instead of reconstructing the entire image, we reconstruct its input features, generated from previous modules. We evaluate our approach on 4 commonly used datasets and 3 commonly used decoder structures on Swin-Tiny. The experiments show that our approach outperforms InfoPro-Transformer, the InfoPro with Transfomer backbone we introduced, by at up to 0.58% on CIFAR-10, CIFAR-100, STL-10 and SVHN datasets, while using up to 12% less memory. Compared to the E2E approach, we require 36% less GPU memory when the network is divided into 2 modules and 45% less GPU memory when the network is divided into 4 modules.

Dense prediction tasks such as segmentation and detection of pathological entities hold crucial clinical value in the digital pathology workflow. However, obtaining dense annotations on large cohorts is usually tedious and expensive. Contrastive learning (CL) is thus often employed to leverage large volumes of unlabeled data to pre-train the backbone network. To boost CL for dense prediction, some studies have proposed variations of dense matching objectives in pre-training. However, our analysis shows that employing existing dense matching strategies on histopathology images enforces invariance among incorrect pairs of dense features and, thus, is imprecise. To address this, we propose a precise location-based matching mechanism that utilizes the overlapping information between geometric transformations to precisely match regions in two augmentations. Extensive experiments on two pretraining datasets (TCGA-BRCA, NCT-CRC-HE) and three downstream datasets (GlaS, CRAG, BCSS) highlight the superiority of our method in semantic and instance segmentation tasks. Our method outperforms previous dense matching methods by up to 7.2 % in average precision for detection and 5.6 % in average precision for instance segmentation tasks. Additionally, by using our matching mechanism in the three popular contrastive learning frameworks, MoCo-v2, VICRegL and ConCL, the average precision in detection is improved by 0.7 % to 5.2 % and the average precision in segmentation is improved by 0.7 % to 4.0 %, demonstrating its generalizability.

This paper introduces a structure-deformable land-air robot which possesses both excellent ground driving and flying ability, with smooth switching mechanism between two modes. The elaborate coupled dynamics model of the proposed robot is established, including rotors, chassis, especially the deformable structures. Furthermore, taking fusion locomotion and complex near-ground situations into consideration, a model based controller is designed for landing and mode switching under various harsh conditions, in which we realise the cooperation between fused two motion modes. The entire system is implemented in ADAMS/Simulink simulation and in practical. We conduct experiments under various complex scenarios. The results show our robot can accomplish land-air switching swiftly and smoothly, and the designed controller can effectively improve the landing flexibility and reliability.

In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos. Compared with 1) the popular unsupervised re-ID setting where the training and test sets are typically under the same domain, and 2) the popular domain generalization (DG) re-ID setting where the training samples are labeled, our novel scenario combines their key challenges: the training samples are unlabeled, and collected form various domains which do no align with the test domain. In other words, we aim to learn a representation in an unsupervised manner and directly use the learned representation for re-ID in novel domains. To fulfill this goal, we make two main contributions: First, we propose Cycle Association (CycAs), a scalable self-supervised learning method for re-ID with low training complexity; and second, we construct a large-scale unlabeled re-ID dataset named LMP-video, tailored for the proposed method. Specifically, CycAs learns re-ID features by enforcing cycle consistency of instance association between temporally successive video frame pairs, and the training cost is merely linear to the data size, making large-scale training possible. On the other hand, the LMP-video dataset is extremely large, containing 50 million unlabeled person images cropped from over 10K Youtube videos, therefore is sufficient to serve as fertile soil for self-supervised learning. Trained on LMP-video, we show that CycAs learns good generalization towards novel domains. The achieved results sometimes even outperform supervised domain generalizable models. Remarkably, CycAs achieves 82.2% Rank-1 on Market-1501 and 49.0% Rank-1 on MSMT17 with zero human annotation, surpassing state-of-the-art supervised DG re-ID methods. Moreover, we also demonstrate the superiority of CycAs under the canonical unsupervised re-ID and the pretrain-and-finetune scenarios.

在许多综合设置（例如视频游戏）和GO中，增强学习（RL）超出了人类的绩效。但是，端到端RL模型的现实部署不太常见，因为RL模型对环境的轻微扰动非常敏感。强大的马尔可夫决策过程（MDP）框架（其中的过渡概率属于名义模型设置的不确定性）提供了一种开发健壮模型的方法。虽然先前的分析表明，RL算法是有效的，假设访问生成模型，但尚不清楚RL在更现实的在线设置下是否可以有效，这需要在探索和开发之间取得仔细的平衡。在这项工作中，我们通过与未知的名义系统进行互动来考虑在线强大的MDP。我们提出了一种强大的乐观策略优化算法，该算法可有效。为了解决由对抗性环境引起的其他不确定性，我们的模型具有通过Fenchel Conjugates得出的新的乐观更新规则。我们的分析确定了在线强大MDP的第一个遗憾。

组织病理学全幻灯片图像（WSIS）在临床研究中起着非常重要的作用，并作为许多癌症诊断的黄金标准。但是，由于其巨大尺寸，生成用于处理WSIS的自动工具是具有挑战性的。当前，为了解决这个问题，传统方法依靠多个实例学习（MIL）策略来处理贴剂级别的WSI。尽管有效，但这种方法在计算上很昂贵，因为将WSI整理成斑块需要时间，并且不探索这些瓷砖之间的空间关系。为了解决这些限制，我们提出了一个本地监督的学习框架，该框架通过探索包含的整个本地和全球信息来处理整个幻灯片。该框架将预训练的网络划分为几个模块，并使用辅助模型在本地优化每个模块。我们还引入了一个随机特征重建单元（RFR），以在训练过程中保留区分特征，并将方法的性能提高1％至3％。对三个公开可用的WSI数据集进行了广泛的实验：TCGA-NSCLC，TCGA-RCC和LKS，突出了我们方法在不同分类任务上的优越性。我们的方法的准确性优于最先进的MIL方法，而高7至10倍。此外，将其分为八个模块时，我们的方法需要端到端培训所需的GPU总内存总数的20％。我们的代码可从https://github.com/cvlab-stonybrook/local_learning_wsi获得。

我们展示了MVLayoutNet，是来自多视图全景的整体三维重建端到端网络。我们的核心贡献是无缝地将学习的单目布局估计和多视图立体声（MV）结合起来，以便在3D和图像空间中准确地重建。我们共同列出布局模块以产生初始布局和新型MVS模块，以获得精确的布局几何形状。与标准MVSNET [33]不同，我们的MVS模块采用新建的布局成本卷，其在相同的深度层中聚合到相应的布局元件中的多视图成本。我们还提供了一种基于注意的方案，指导MVS模块专注于结构区域。这种设计考虑了本地像素级成本和全球整体信息，以便更好地重建。实验表明，我们的方法在2D-3D-S [1]和Zind [5]数据集中，在深度RMSE方面以21.7％和20.6％表示最先进的。最后，我们的方法导致连贯的布局几何，使整个场景的重建能够。

Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications' boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy through either deeper or wider network structures, which brings with them the exponential increment of the computational and storage cost, delaying the responding time.In this paper, we propose a general training framework named self distillation, which notably enhances the performance (accuracy) of convolutional neural networks through shrinking the size of the network rather than aggrandizing it. Different from traditional knowledge distillation -a knowledge transformation methodology among networks, which forces student neural networks to approximate the softmax layer outputs of pre-trained teacher neural networks, the proposed self distillation framework distills knowledge within network itself. The networks are firstly divided into several sections. Then the knowledge in the deeper portion of the networks is squeezed into the shallow ones. Experiments further prove the generalization of the proposed self distillation framework: enhancement of accuracy at average level is 2.65%, varying from 0.61% in ResNeXt as minimum to 4.07% in VGG19 as maximum. In addition, it can also provide flexibility of depth-wise scalable inference on resource-limited edge devices. Our codes will be released on github soon.

Digital engineering transformation is a crucial process for the engineering paradigm shifts in the fourth industrial revolution (4IR), and artificial intelligence (AI) is a critical enabling technology in digital engineering transformation. This article discusses the following research questions: What are the fundamental changes in the 4IR? More specifically, what are the fundamental changes in engineering? What is digital engineering? What are the main uncertainties there? What is trustworthy AI? Why is it important today? What are emerging engineering paradigm shifts in the 4IR? What is the relationship between the data-intensive paradigm and digital engineering transformation? What should we do for digitalization? From investigating the pattern of industrial revolutions, this article argues that ubiquitous machine intelligence (uMI) is the defining power brought by the 4IR. Digitalization is a condition to leverage ubiquitous machine intelligence. Digital engineering transformation towards Industry 4.0 has three essential building blocks: digitalization of engineering, leveraging ubiquitous machine intelligence, and building digital trust and security. The engineering design community at large is facing an excellent opportunity to bring the new capabilities of ubiquitous machine intelligence and trustworthy AI principles, as well as digital trust, together in various engineering systems design to ensure the trustworthiness of systems in Industry 4.0.

Autonomous driving is an exciting new industry, posing important research questions. Within the perception module, 3D human pose estimation is an emerging technology, which can enable the autonomous vehicle to perceive and understand the subtle and complex behaviors of pedestrians. While hardware systems and sensors have dramatically improved over the decades -- with cars potentially boasting complex LiDAR and vision systems and with a growing expansion of the available body of dedicated datasets for this newly available information -- not much work has been done to harness these novel signals for the core problem of 3D human pose estimation. Our method, which we coin HUM3DIL (HUMan 3D from Images and LiDAR), efficiently makes use of these complementary signals, in a semi-supervised fashion and outperforms existing methods with a large margin. It is a fast and compact model for onboard deployment. Specifically, we embed LiDAR points into pixel-aligned multi-modal features, which we pass through a sequence of Transformer refinement stages. Quantitative experiments on the Waymo Open Dataset support these claims, where we achieve state-of-the-art results on the task of 3D pose estimation.