Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images. Spatial-domain information has been widely exploited to implement image SR, so a new trend is to involve frequency-domain information in SR tasks. Besides, image SR is typically application-oriented and various computer vision tasks call for image arbitrary magnification. Therefore, in this paper, we study image features in the frequency domain to design a novel scale-arbitrary image SR network. First, we statistically analyze LR-HR image pairs of several datasets under different scale factors and find that the high-frequency spectra of different images under different scale factors suffer from different degrees of degradation, but the valid low-frequency spectra tend to be retained within a certain distribution range. Then, based on this finding, we devise an adaptive scale-aware feature division mechanism using deep reinforcement learning, which can accurately and adaptively divide the frequency spectrum into the low-frequency part to be retained and the high-frequency one to be recovered. Finally, we design a scale-aware feature recovery module to capture and fuse multi-level features for reconstructing the high-frequency spectrum at arbitrary scale factors. Extensive experiments on public datasets show the superiority of our method compared with state-of-the-art methods.

Detecting abnormal crowd motion emerging from complex interactions of individuals is paramount to ensure the safety of crowds. Crowd-level abnormal behaviors (CABs), e.g., counter flow and crowd turbulence, are proven to be the crucial causes of many crowd disasters. In the recent decade, video anomaly detection (VAD) techniques have achieved remarkable success in detecting individual-level abnormal behaviors (e.g., sudden running, fighting and stealing), but research on VAD for CABs is rather limited. Unlike individual-level anomaly, CABs usually do not exhibit salient difference from the normal behaviors when observed locally, and the scale of CABs could vary from one scenario to another. In this paper, we present a systematic study to tackle the important problem of VAD for CABs with a novel crowd motion learning framework, multi-scale motion consistency network (MSMC-Net). MSMC-Net first captures the spatial and temporal crowd motion consistency information in a graph representation. Then, it simultaneously trains multiple feature graphs constructed at different scales to capture rich crowd patterns. An attention network is used to adaptively fuse the multi-scale features for better CAB detection. For the empirical study, we consider three large-scale crowd event datasets, UMN, Hajj and Love Parade. Experimental results show that MSMC-Net could substantially improve the state-of-the-art performance on all the datasets.

Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality ground-truth data hinders their applications due to the generalization problem. Recently, Implicit Neural Representation (INR) has appeared as a powerful DL-based tool for solving the inverse problem by characterizing the attributes of a signal as a continuous function of corresponding coordinates in an unsupervised manner. In this work, we proposed an INR-based method to improve dynamic MRI reconstruction from highly undersampled k-space data, which only takes spatiotemporal coordinates as inputs. Specifically, the proposed INR represents the dynamic MRI images as an implicit function and encodes them into neural networks. The weights of the network are learned from sparsely-acquired (k, t)-space data itself only, without external training datasets or prior images. Benefiting from the strong implicit continuity regularization of INR together with explicit regularization for low-rankness and sparsity, our proposed method outperforms the compared scan-specific methods at various acceleration factors. E.g., experiments on retrospective cardiac cine datasets show an improvement of 5.5 ~ 7.1 dB in PSNR for extremely high accelerations (up to 41.6-fold). The high-quality and inner continuity of the images provided by INR has great potential to further improve the spatiotemporal resolution of dynamic MRI, without the need of any training data.

Computer vision applications in intelligent transportation systems (ITS) and autonomous driving (AD) have gravitated towards deep neural network architectures in recent years. While performance seems to be improving on benchmark datasets, many real-world challenges are yet to be adequately considered in research. This paper conducted an extensive literature review on the applications of computer vision in ITS and AD, and discusses challenges related to data, models, and complex urban environments. The data challenges are associated with the collection and labeling of training data and its relevance to real world conditions, bias inherent in datasets, the high volume of data needed to be processed, and privacy concerns. Deep learning (DL) models are commonly too complex for real-time processing on embedded hardware, lack explainability and generalizability, and are hard to test in real-world settings. Complex urban traffic environments have irregular lighting and occlusions, and surveillance cameras can be mounted at a variety of angles, gather dirt, shake in the wind, while the traffic conditions are highly heterogeneous, with violation of rules and complex interactions in crowded scenarios. Some representative applications that suffer from these problems are traffic flow estimation, congestion detection, autonomous driving perception, vehicle interaction, and edge computing for practical deployment. The possible ways of dealing with the challenges are also explored while prioritizing practical deployment.

尽管将进化计算整合到增强学习中的新进展，但缺乏高性能平台可赋予合成性和大规模的并行性，这对与异步商业游戏相关的研究和应用造成了非平凡的困难。在这里，我们介绍了Lamarckian-一个开源平台，其支持进化增强学习可扩展到分布式计算资源的支持。为了提高训练速度和数据效率，拉马克人采用了优化的通信方法和异步进化增强学习工作流程。为了满足商业游戏和各种方法对异步界面的需求，Lamarckian量身定制了异步的马尔可夫决策过程界面，并设计了带有脱钩模块的面向对象的软件体系结构。与最先进的RLLIB相比，我们从经验上证明了Lamarckian在基准测试中具有多达6000 CPU核心的独特优势：i）i）在Google足球游戏上运行PPO时，采样效率和训练速度都翻了一番； ii）在乒乓球比赛中运行PBT+PPO时，训练速度的速度快13倍。此外，我们还提出了两种用例：i）如何将拉马克安应用于生成行为多样性游戏AI； ii）Lamarckian如何应用于游戏平衡测试的异步商业游戏。

在目前的工作中，我们提出了一个自制的坐标投影网络（范围），以通过解决逆断层扫描成像问题来从单个SV正弦图中重建无伪像的CT图像。与使用隐式神经代表网络（INR）解决类似问题的最新相关工作相比，我们的基本贡献是一种有效而简单的重新注射策略，可以将层析成像图像重建质量推向监督的深度学习CT重建工作。提出的策略是受线性代数与反问题之间的简单关系的启发。为了求解未确定的线性方程式系统，我们首先引入INR以通过图像连续性之前限制解决方案空间并实现粗糙解决方案。其次，我们建议生成一个密集的视图正式图，以改善线性方程系统的等级并产生更稳定的CT图像解决方案空间。我们的实验结果表明，重新投影策略显着提高了图像重建质量（至少为PSNR的+3 dB）。此外，我们将最近的哈希编码集成到我们的范围模型中，这极大地加速了模型培训。最后，我们评估并联和风扇X射线梁SVCT重建任务的范围。实验结果表明，所提出的范围模型优于两种基于INR的方法和两种受欢迎的监督DL方法。

基于神经影像数据的自闭症谱系障碍（ASD）的准确诊断具有重要意义，因为从ASD检测中提取有用的神经影像学数据很具有挑战性。即使已经利用了机器学习技术来改善从神经影像数据中提取信息，但由不同的元数据条件（即数据收集策略）引起的不同数据质量限制了可以提取的有效信息，从而导致数据依赖于数据ASD检测中的预测精度，在某些情况下可能比随机猜测要糟糕。在这项工作中，我们系统地研究了三种元数据对基于从20个不同位点收集的结构MRI分类的预测准确性的影响，其中元数据条件有所不同。

With the increased usage of AI accelerators on mobile and edge devices, on-device machine learning (ML) is gaining popularity. Thousands of proprietary ML models are being deployed today on billions of untrusted devices. This raises serious security concerns about model privacy. However, protecting model privacy without losing access to the untrusted AI accelerators is a challenging problem. In this paper, we present a novel on-device model inference system, ShadowNet. ShadowNet protects the model privacy with Trusted Execution Environment (TEE) while securely outsourcing the heavy linear layers of the model to the untrusted hardware accelerators. ShadowNet achieves this by transforming the weights of the linear layers before outsourcing them and restoring the results inside the TEE. The non-linear layers are also kept secure inside the TEE. ShadowNet's design ensures efficient transformation of the weights and the subsequent restoration of the results. We build a ShadowNet prototype based on TensorFlow Lite and evaluate it on five popular CNNs, namely, MobileNet, ResNet-44, MiniVGG, ResNet-404, and YOLOv4-tiny. Our evaluation shows that ShadowNet achieves strong security guarantees with reasonable performance, offering a practical solution for secure on-device model inference.

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This paper proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It increases the randomness (diversity) by drawing the cut-points randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest generally outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 35 classification and regression datasets. Remarkably, BoostForest tunes its parameters by simply sampling them randomly from a parameter pool, which can be easily specified, and its ensemble learning framework can also be used to combine many other base learners.

Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.