Hierarchical semantic structures, naturally existing in real-world datasets, can assist in capturing the latent distribution of data to learn robust hash codes for retrieval systems. Although hierarchical semantic structures can be simply expressed by integrating semantically relevant data into a high-level taxon with coarser-grained semantics, the construction, embedding, and exploitation of the structures remain tricky for unsupervised hash learning. To tackle these problems, we propose a novel unsupervised hashing method named Hyperbolic Hierarchical Contrastive Hashing (HHCH). We propose to embed continuous hash codes into hyperbolic space for accurate semantic expression since embedding hierarchies in hyperbolic space generates less distortion than in hyper-sphere space and Euclidean space. In addition, we extend the K-Means algorithm to hyperbolic space and perform the proposed hierarchical hyperbolic K-Means algorithm to construct hierarchical semantic structures adaptively. To exploit the hierarchical semantic structures in hyperbolic space, we designed the hierarchical contrastive learning algorithm, including hierarchical instance-wise and hierarchical prototype-wise contrastive learning. Extensive experiments on four benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art unsupervised hashing methods. Codes will be released.

Referring image segmentation aims at localizing all pixels of the visual objects described by a natural language sentence. Previous works learn to straightforwardly align the sentence embedding and pixel-level embedding for highlighting the referred objects, but ignore the semantic consistency of pixels within the same object, leading to incomplete masks and localization errors in predictions. To tackle this problem, we propose CoupAlign, a simple yet effective multi-level visual-semantic alignment method, to couple sentence-mask alignment with word-pixel alignment to enforce object mask constraint for achieving more accurate localization and segmentation. Specifically, the Word-Pixel Alignment (WPA) module performs early fusion of linguistic and pixel-level features in intermediate layers of the vision and language encoders. Based on the word-pixel aligned embedding, a set of mask proposals are generated to hypothesize possible objects. Then in the Sentence-Mask Alignment (SMA) module, the masks are weighted by the sentence embedding to localize the referred object, and finally projected back to aggregate the pixels for the target. To further enhance the learning of the two alignment modules, an auxiliary loss is designed to contrast the foreground and background pixels. By hierarchically aligning pixels and masks with linguistic features, our CoupAlign captures the pixel coherence at both visual and semantic levels, thus generating more accurate predictions. Extensive experiments on popular datasets (e.g., RefCOCO and G-Ref) show that our method achieves consistent improvements over state-of-the-art methods, e.g., about 2% oIoU increase on the validation and testing set of RefCOCO. Especially, CoupAlign has remarkable ability in distinguishing the target from multiple objects of the same class.

Machine learning has been widely used in healthcare applications to approximate complex models, for clinical diagnosis, prognosis, and treatment. As deep learning has the outstanding ability to extract information from time series, its true capabilities on sparse, irregularly sampled, multivariate, and imbalanced physiological data are not yet fully explored. In this paper, we systematically examine the performance of machine learning models for the clinical prediction task based on the EHR, especially physiological time series. We choose Physionet 2019 challenge public dataset to predict Sepsis outcomes in ICU units. Ten baseline machine learning models are compared, including 3 deep learning methods and 7 non-deep learning methods, commonly used in the clinical prediction domain. Nine evaluation metrics with specific clinical implications are used to assess the performance of models. Besides, we sub-sample training dataset sizes and use learning curve fit to investigate the impact of the training dataset size on the performance of the machine learning models. We also propose the general pre-processing method for the physiology time-series data and use Dice Loss to deal with the dataset imbalanced problem. The results show that deep learning indeed outperforms non-deep learning, but with certain conditions: firstly, evaluating with some particular evaluation metrics (AUROC, AUPRC, Sensitivity, and FNR), but not others; secondly, the training dataset size is large enough (with an estimation of a magnitude of thousands).

The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing. In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based image signal processing (ISP) pipeline replacing the standard mobile ISPs that can run on modern smartphone GPUs using TensorFlow Lite. The participants were provided with a large-scale Fujifilm UltraISP dataset consisting of thousands of paired photos captured with a normal mobile camera sensor and a professional 102MP medium-format FujiFilm GFX100 camera. The runtime of the resulting models was evaluated on the Snapdragon's 8 Gen 1 GPU that provides excellent acceleration results for the majority of common deep learning ops. The proposed solutions are compatible with all recent mobile GPUs, being able to process Full HD photos in less than 20-50 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.

随着卷积神经网络（CNN）的蓬勃发展，诸如VGG-16和Resnet-50之类的CNN广泛用作SAR船检测中的骨架。但是，基于CNN的骨干很难对远程依赖性进行建模，并且导致缺乏浅层特征图中缺乏足够的高质量语义信息，从而导致在复杂的背景和小型船只中的检测性能不佳。为了解决这些问题，我们提出了一种基于SWIN Transformer的SAR船检测方法，并提出了功能增强功能功能金字塔网络（FEFPN）。SWIN Transformer用作建模远程依赖性并生成层次特征图的骨架。提出了FEFPN，以进一步提高特征地图的质量，通过逐渐增强各级特征地图的语义信息，尤其是浅层中的特征地图。在SAR船检测数据集（SSDD）上进行的实验揭示了我们提出的方法的优势。

多年来，Yolo系列一直是有效对象检测的事实上的行业级别标准。尤洛社区（Yolo Community）绝大多数繁荣，以丰富其在众多硬件平台和丰富场景中的使用。在这份技术报告中，我们努力将其限制推向新的水平，以坚定不移的行业应用心态前进。考虑到对真实环境中速度和准确性的多种要求，我们广泛研究了行业或学术界的最新对象检测进步。具体而言，我们从最近的网络设计，培训策略，测试技术，量化和优化方法中大量吸收了思想。最重要的是，我们整合了思想和实践，以在各种规模上建立一套可供部署的网络，以适应多元化的用例。在Yolo作者的慷慨许可下，我们将其命名为Yolov6。我们还向用户和贡献者表示热烈欢迎，以进一步增强。为了了解性能，我们的Yolov6-N在NVIDIA TESLA T4 GPU上以1234 fps的吞吐量在可可数据集上击中35.9％的AP。 Yolov6-S在495 fps处的43.5％AP罢工，在相同规模〜（Yolov5-S，Yolox-S和Ppyoloe-S）上超过其他主流探测器。我们的量化版本的Yolov6-S甚至在869 fps中带来了新的43.3％AP。此外，与其他推理速度相似的检测器相比，Yolov6-m/L的精度性能（即49.5％/52.3％）更好。我们仔细进行了实验以验证每个组件的有效性。我们的代码可在https://github.com/meituan/yolov6上提供。

快速对抗训练（脂肪）有效地提高了标准对抗训练（SAT）的效率。然而，初始脂肪遇到灾难性的过度拟合，即，对抗性攻击的稳健精度突然并大大减少。尽管有几种脂肪变体毫不费力地防止过度拟合，但他们牺牲了很多计算成本。在本文中，我们探讨了SAT和FAT的训练过程之间的差异，并观察到，对抗性实例（AES）脂肪的攻击成功率在后期训练阶段逐渐变得更糟，从而导致过度拟合。 AE是通过零或随机初始化的快速梯度标志方法（FGSM）生成的。根据观察结果，我们提出了一种先前的FGSM初始化方法，以避免在研究多种初始化策略后避免过度适应，从而在整个训练过程中提高了AE的质量。初始化是通过利用历史上生成的AE而没有额外计算成本而形成的。我们进一步为提出的初始化方法提供了理论分析。我们还基于先前的初始化，即当前生成的扰动不应过多地偏离先前引导的初始化，因此我们还提出了一个简单而有效的正规化程序。正常化器同时采用历史和当前的对抗性扰动来指导模型学习。在四个数据集上进行的评估表明，所提出的方法可以防止灾难性过度拟合和优于最先进的脂肪方法。该代码在https://github.com/jiaxiaojunqaq/fgsm-pgi上发布。

在本文中，我们介绍了在集中差异隐私（ZCDP）下进行协方差估计的两种新算法。第一个算法达到了$ \ tilde {o}（d^{1/4} \ sqrt {\ mathrm {tr}}/\ sqrt {n} + \ sqrt {d}/n）$的frobenius错误\ mathrm {tr} $是协方差矩阵的跟踪。通过服用$ \ mathrm {tr} = 1 $，这也意味着$ \ tilde {o}的最坏情况错误绑定（d^{1/4}/\ sqrt {n}）$，它改善了标准高斯机制的$ \ tilde {o}（d/n）$用于制度$ d> \ widetilde {\ omega}（n^{2/3}）$。我们的第二个算法提供了一种对尾敏感的界限，在偏斜的数据上可能会更好。相应的算法也很简单有效。实验结果表明，它们对先前的工作提供了重大改进。

媒体中的人员搜索已经看到互联网应用程序的潜力，例如视频剪辑和字符集。这项任务很常见，但忽略了以前的人员搜索工作，专注于监视场景。媒体情景从监视场景中有一些不同的挑战。例如，一个人可能经常改变衣服。为了减轻这个问题，本文提出了一个统一的探测器和图形网络（UDGNET），用于媒体中的人员搜索。 UDGNET是第一个检测和重新识别人体和头部的第一个人搜索框架。具体地，它首先基于统一网络构建两个分支以检测人体和头部，然后检测到的主体和头部用于重新识别。这种双重任务方法可以显着增强歧视性学习。为了解决布料不断变化的问题，UDGNET构建了两个图形，以探索布换器样本中的可靠链接，并利用图形网络来学习更好的嵌入。这种设计有效地增强了人们搜索的鲁棒性，以改变布什挑战。此外，我们证明了UDGNET可以通过基于锚和无锚的人搜索框架来实现，并进一步实现性能改进。本文还为媒体（PSM）中的人员搜索提供了大规模数据集，其提供身体和头部注释。它是迄今为止媒体搜索的最大数据集。实验表明，UDGNET在MAP中通过12.1％提高了Anipor的模型。同时，它在监控和长期情景中显示出良好的概括。数据集和代码将可用：https://github.com/shuxjweb/psm.git。

几乎所有现有的基于面部动作编码系统的数据集包括面部动作单元（AU）强度信息使用A-E级别分层地向强度值注释。然而，面部表情连续变化，并将从一个状态变为另一个状态。因此，将局部面部AU的强度值重新播出以表示整个面部表情的变化更有效，特别是在表达转移和面部动画的领域。我们将Feafa的扩展与重新标记的DISFA数据库相结合，可在HTTPS://www.iiplab.net/feafa+ /现在提供。扩展Feafa（Feafa +）包括来自Feafa和Disfa的150个视频序列，总共230,184帧，使用表达式定量工具手动注释24重新定义AU的浮点强度值。我们还列出了针对构成和自发子集的粗略数值结果，并为AU强度回归任务提供基线比较。