Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics are relatively small but not infinitesimal, thus fitting well with the practical implementation of neural networks. Currently, discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization, i.e. landscape analysis. It mainly focuses on gradient regions, such as saddle points and local minima. We theoretically establish the connection between saddle point escaping (SPE) stages and the matrix rank in DMF. We prove that, for a rank-R matrix reconstruction, DMF will converge to a second-order critical point after R stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. This work provides a new theory to analyze implicit regularization in deep learning.

Single-frame InfraRed Small Target (SIRST) detection has been a challenging task due to a lack of inherent characteristics, imprecise bounding box regression, a scarcity of real-world datasets, and sensitive localization evaluation. In this paper, we propose a comprehensive solution to these challenges. First, we find that the existing anchor-free label assignment method is prone to mislabeling small targets as background, leading to their omission by detectors. To overcome this issue, we propose an all-scale pseudo-box-based label assignment scheme that relaxes the constraints on scale and decouples the spatial assignment from the size of the ground-truth target. Second, motivated by the structured prior of feature pyramids, we introduce the one-stage cascade refinement network (OSCAR), which uses the high-level head as soft proposals for the low-level refinement head. This allows OSCAR to process the same target in a cascade coarse-to-fine manner. Finally, we present a new research benchmark for infrared small target detection, consisting of the SIRST-V2 dataset of real-world, high-resolution single-frame targets, the normalized contrast evaluation metric, and the DeepInfrared toolkit for detection. We conduct extensive ablation studies to evaluate the components of OSCAR and compare its performance to state-of-the-art model-driven and data-driven methods on the SIRST-V2 benchmark. Our results demonstrate that a top-down cascade refinement framework can improve the accuracy of infrared small target detection without sacrificing efficiency. The DeepInfrared toolkit, dataset, and trained models are available at https://github.com/YimianDai/open-deepinfrared to advance further research in this field.

在本文中，我们研究了基于骨架的动作识别的问题，该问题在学习从基础阶级到新颖类的可转移表示方面构成了独特的挑战，尤其是针对细粒度的动作。现有的元学习框架通常依赖于空间维度中的身体级表示，这限制了概括以捕获细粒标签空间中细微的视觉差异。为了克服上述局限性，我们提出了一种基于单发骨架的动作识别的部分感知的原型代表。我们的方法捕获了两个独特的空间级别的骨架运动模式，一种用于所有身体关节的全球环境，称为身体水平，另一个则参与了身体部位的局部空间区域，称为零件水平。我们还设计了一种类不足的注意机制，以突出每个动作类别的重要部分。具体而言，我们开发了一个由三个模块组成的零件感知原型图网络：我们的双层建模的级联嵌入模块，一个基于注意力的零件融合模块，用于融合零件并生成零件感知的原型，以及可以执行匹配的模块。与部分意识表示的分类。我们证明了我们方法对两个基于公共骨架的动作识别数据集的有效性：NTU RGB+D 120和NW-UCLA。

$ t_ {1 \ rho} $映射是一种有希望的定量MRI技术，用于对组织性质的非侵入性评估。基于学习的方法可以从减少数量的$ t_ {1 \ rho} $加权图像中映射$ t_ {1 \ rho} $，但需要大量的高质量培训数据。此外，现有方法不提供$ t_ {1 \ rho} $估计的置信度。为了解决这些问题，我们提出了一个自我监督的学习神经网络，该网络使用学习过程中的放松约束来学习$ t_ {1 \ rho} $映射。为$ t_ {1 \ rho} $量化网络建立了认知不确定性和态度不确定性，以提供$ t_ {1 \ rho} $映射的贝叶斯置信度估计。不确定性估计还可以使模型规范化，以防止其学习不完美的数据。我们对52例非酒精性脂肪肝病患者收集的$ T_ {1 \ rho} $数据进行了实验。结果表明，我们的方法优于$ t_ {1 \ rho} $量化肝脏的现有方法，使用少于两个$ t_ {1 \ rho} $加权图像。我们的不确定性估计提供了一种可行的方法，可以建模基于自我监督学习的$ t_ {1 \ rho} $估计的信心，这与肝脏中的现实$ t_ {1 \ rho} $成像是一致的。

结构光（SL）系统以主动照明投影获得高保真3D几何形状。当在具有强烈的环境照明，全球照明和跨设备干扰的环境中工作时，常规系统会出现挑战。本文提出了一种通用技术，以通过投影除天然SL模式来预测冗余光学信号来提高SL的鲁棒性。这样，预计的信号与错误更具区别。因此，可以使用简单的信号处理更容易地恢复几何信息，并获得``性能中的编码增益''。我们使用冗余代码提出了三个应用程序：（1）在强环境光下进行SL成像的自我错误校正，（（（ 2）在全球照明下自适应重建的错误检测，以及（3）使用设备特定的投影序列编码的干扰过滤，尤其是针对基于事件摄像机的SL和灯窗帘设备。我们系统地分析了这些应用中的设计规则和信号处理算法。相应的硬件原型是用于在现实世界复杂场景上进行评估的。合成和真实数据的实验结果证明了具有冗余代码的SL系统的显着性能改进。

分层多粒度分类（HMC）将分层多粒度标签分配给每个对象，专注于对标签层次结构进行编码，例如[“Albatross”，“Laysan Albatross”]从粗略级别进行。然而，细粒度的定义是主观的，并且图像质量可能会影响识别。因此，可以在层次结构的任何水平处观察样本，例如，例如，[“信天翁”]或[“白金贸易”，“Laysan Albatross”，并且在致动类别中辨别的示例在HMC的传统设置中通常被忽略。在本文中，我们研究了HMC问题，其中对象在层次结构的任何级别上标记。所提出的方法的基本设计源自两个动机：（1）学习在各个级别标记的物体应该转移级别之间的分层知识; （2）较低级别的类应继承与上级超类相关的属性。所提出的组合损失通过从树层次结构中定义的相关标签聚合信息来最大化观察到的地面真实标签的边际概率。如果观察到的标签处于叶片水平，则组合损失进一步施加了多级跨熵损失，以增加细粒度分类损失的重量。考虑到分层特征交互，我们提出了一个分层剩余网络（HRN），其中来自父级的粒度特定特征作为残留连接的特定特征被添加到儿童级别的特征。与最先进的HMC方法和精细的视觉分类（FGVC）方法相比，三种常用数据集的实验证明了我们的方法的有效性和利用标签层次结构的方法。

互动学习和决策的基本挑战，从强盗问题到加固学习，是提供了实现的采样效率，自适应学习算法，实现了近乎最佳的遗憾。这个问题类似于最佳（监督）统计学习的经典问题，其中有众所周知的复杂性措施（例如，VC维度和Rademacher复杂性），用于控制学习的统计复杂性。然而，由于问题的适应性，表征交互式学习的统计复杂性基本上更具挑战性。这项工作的主要结果提供了复杂性措施，决策系数，被证明是必要的，并且足以用于采样有效的互动学习。特别是，我们提供：1。对于任何交互式决策问题的最佳遗憾的下限，将决策估计系数作为基本限制建立。 2.统一算法设计原理，估算到决策（E2D），它将任何用于监督估算的算法转换为决策的在线算法。 E2D遗憾的是符合我们下限的遗憾，从而实现了最佳的样本高效学习，其特征在于决策估计系数。一起参加，这些结果构成了互动决策的可读性理论。当应用于增强学习设置时，决策估计系数基本上恢复所有现有的硬度结果和下限。更广泛地，该方法可以被视为统计估算的经典LE CAM理论的决策理论;它还统一了许多现有方法 - 贝叶斯和频繁的方法。

自我监督学习（SSL）在语音识别方面取得了巨大的成功，而有限的探索已尝试完成其他语音处理任务。由于语音信号包含多方面的信息，包括说话者身份，副语言学，口语内容等，学习所有语音任务的通用表示都具有挑战性。为了解决该问题，我们提出了一个新的预培训模型WAVLM，以解决全堆栈的下游语音任务。 Wavlm共同学习了蒙面的语音预测和预训练。通过这种方式，WAVLM不仅可以通过掩盖的语音预测来保持语音内容建模能力，而且还可以通过语音denoing来提高非ASR任务的潜力。此外，WAVLM还采用封闭式的变压器结构的封闭相对位置偏置，以更好地捕获输入语音的序列排序。我们还将培训数据集从60k小时扩展到94K小时。 WAVLM大型在精湛的基准上实现了最先进的性能，并在其代表性基准上为各种语音处理任务带来了重大改进。代码和预培训模型可在https://aka.ms/wavlm上找到。

This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.

The development of social media user stance detection and bot detection methods rely heavily on large-scale and high-quality benchmarks. However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research. To address these issues, we propose a Multi-Relational Graph-Based Twitter Account Detection Benchmark (MGTAB), the first standardized graph-based benchmark for account detection. To our knowledge, MGTAB was built based on the largest original data in the field, with over 1.55 million users and 130 million tweets. MGTAB contains 10,199 expert-annotated users and 7 types of relationships, ensuring high-quality annotation and diversified relations. In MGTAB, we extracted the 20 user property features with the greatest information gain and user tweet features as the user features. In addition, we performed a thorough evaluation of MGTAB and other public datasets. Our experiments found that graph-based approaches are generally more effective than feature-based approaches and perform better when introducing multiple relations. By analyzing experiment results, we identify effective approaches for account detection and provide potential future research directions in this field. Our benchmark and standardized evaluation procedures are freely available at: https://github.com/GraphDetec/MGTAB.