Face Restoration (FR) aims to restore High-Quality (HQ) faces from Low-Quality (LQ) input images, which is a domain-specific image restoration problem in the low-level computer vision area. The early face restoration methods mainly use statistic priors and degradation models, which are difficult to meet the requirements of real-world applications in practice. In recent years, face restoration has witnessed great progress after stepping into the deep learning era. However, there are few works to study deep learning-based face restoration methods systematically. Thus, this paper comprehensively surveys recent advances in deep learning techniques for face restoration. Specifically, we first summarize different problem formulations and analyze the characteristic of the face image. Second, we discuss the challenges of face restoration. Concerning these challenges, we present a comprehensive review of existing FR methods, including prior based methods and deep learning-based methods. Then, we explore developed techniques in the task of FR covering network architectures, loss functions, and benchmark datasets. We also conduct a systematic benchmark evaluation on representative methods. Finally, we discuss future directions, including network designs, metrics, benchmark datasets, applications,etc. We also provide an open-source repository for all the discussed methods, which is available at https://github.com/TaoWangzj/Awesome-Face-Restoration.

知识蒸馏（KD）显示了其对象检测的有效性，在AI知识（教师检测器）和人类知识（人类专家）的监督下，它在该物体检测中训练紧凑的对象检测器。但是，现有研究一致地对待AI知识和人类知识，并在学习过程中采用统一的数据增强策略，这将导致对多尺度对象的学习有偏见，并且对教师探测器的学习不足，从而导致不满意的蒸馏性能。为了解决这些问题，我们提出了特定于样本的数据增强和对抗性功能增强。首先，为了减轻多尺度对象产生的影响，我们根据傅立叶角度的观察结果提出了自适应数据增强。其次，我们提出了一种基于对抗性示例的功能增强方法，以更好地模仿AI知识以弥补教师探测器的信息不足。此外，我们提出的方法是统一的，并且很容易扩展到其他KD方法。广泛的实验证明了我们的框架的有效性，并在一阶段和两阶段探测器中提高了最先进方法的性能，最多可以带来0.5 MAP的增长。

大规模图在现实情况下无处不在，可以通过图神经网络（GNN）训练以生成下游任务的表示形式。鉴于大规模图的丰富信息和复杂的拓扑结构，我们认为在这样的图中存在冗余，并将降低训练效率。不幸的是，模型可伸缩性严重限制了通过香草GNNS训练大规模图的效率。尽管在基于抽样的培训方法方面取得了最新进展，但基于抽样的GNN通常忽略了冗余问题。在大规模图上训练这些型号仍然需要无法容忍的时间。因此，我们建议通过重新思考图中的固有特征来降低冗余并提高使用GNN的大规模训练效率。在本文中，我们开拓者提出了一种称为dropreef的曾经使用的方法，以在大规模图中删除冗余。具体而言，我们首先进行初步实验，以探索大规模图中的潜在冗余。接下来，我们提出一个度量标准，以量化图中所有节点的异质性。基于实验和理论分析，我们揭示了大规模图中的冗余，即具有高邻居异质的节点和大量邻居。然后，我们建议Dropreef一劳永逸地检测并删除大规模图中的冗余，以帮助减少训练时间，同时确保模型准确性没有牺牲。为了证明DropReef的有效性，我们将其应用于最新的基于最新的采样GNN，用于训练大规模图，这是由于此类模型的高精度。使用Dropreef杠杆，可以大力提高模型的训练效率。 Dropreef高度兼容，并且在离线上执行，从而在很大程度上使目前和未来的最新采样GNN受益。

作为一种常见的安全工具，已广泛应用可见的水印来保护数字图像的版权。但是，最近的作品表明，可见的水印可以通过DNN删除而不会损坏其宿主图像。这样的水印驱动技术对图像的所有权构成了巨大威胁。受到DNN在对抗扰动方面的脆弱性的启发，我们提出了一种新颖的防御机制，可以永久地通过对抗机器学习。从对手的角度来看，可以将盲水水印网络作为我们的目标模型提出。然后，我们实际上优化了对宿主图像上不可察觉的对抗扰动，以主动攻击水印网络，称为水印疫苗。具体而言，提出了两种类型的疫苗。破坏水印疫苗（DWV）在通过水印拆除网络后，诱导了与水印一起破坏宿主图像。相比之下，不可行的水印疫苗（IWV）以另一种方式试图保持水印不清除且仍然明显。广泛的实验证明了我们的DWV/IWV在防止水印去除方面的有效性，尤其是在各种水印去除网络上。

由于成像硬件和重建算法的重大进展，计算成像拐角处或非视线（NLOS）成像的方法正在成为现实。 NAM等人的最新发展NLOS成像。展示了一个高速非焦距成像系统，其运行速度为5Hz，比以前的ART快100倍。然而，这种巨大的采集率增长需要在光传输中进行大量近似，打破了许多现有的NLOS重建方法，这些方法采用了理想化的图像形成模型。为了弥合差距，我们提出了一个新颖的深层模型，该模型结合了波传播和体积渲染的互补物理学先验，以进行高质量和强大的NLOS重建。该精心策划的设计通过放松图像形成模型来规范解决方案空间，从而产生了一个深层模型，尽管在合成数据上只接受了专门的培训，但在真实捕获上却很好地概括了。此外，我们设计了一个统一的学习框架，使我们的模型能够使用各种监督信号（包括目标强度图像甚至RAW NLOS瞬态测量）灵活训练我们的模型。一旦受过训练，我们的模型就会在一次前传球中的推理时间呈现强度和深度图像，能够在高端GPU上处理超过5个以上的捕获。通过广泛的定性和定量实验，我们表明我们的方法的表现优于先前的物理和基于学习的方法，同时基于合成和实际测量。我们预计，我们的方法以及快速捕获系统将加速NLOS成像的未来开发，用于需要高速成像的现实世界应用。

采样是图形神经网络（GNN）培训的关键操作，有助于降低成本。以前的文献已经通过数学和统计方法探索了改进采样算法。但是，采样算法和硬件之间存在差距。在不考虑硬件的情况下，算法设计人员仅在算法级别优化采样，缺少通过利用硬件功能来促进现有采样算法效率的巨大潜力。在本文中，我们开创了一个为主流采样算法提出的统一编程模型，称为GNNSampler，涵盖了各个类别中采样算法的关键过程。其次，为了利用硬件功能，我们选择数据局部性作为案例研究，并在图中探索节点及其邻居之间的数据位置，以减轻采样中不规则的内存访问。第三，我们在GNNSampler中实现了各种采样算法的局部感知优化，以优化一般的采样过程。最后，我们强调在大图数据集上进行实验，以分析训练时间，准确性和硬件级指标之间的相关性。广泛的实验表明，我们的方法通用到主流采样算法，并有助于大大减少训练时间，尤其是在大规模图中。

Uncertainty quantification (UQ) plays a pivotal role in the reduction of uncertainties during both optimization and decision making, applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two of the most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlight the fundamental research challenges and directions associated with the UQ field.

Graph neural networks (GNNs) have been demonstrated to be a powerful algorithmic model in broad application fields for their effectiveness in learning over graphs. To scale GNN training up for large-scale and ever-growing graphs, the most promising solution is distributed training which distributes the workload of training across multiple computing nodes. However, the workflows, computational patterns, communication patterns, and optimization techniques of distributed GNN training remain preliminarily understood. In this paper, we provide a comprehensive survey of distributed GNN training by investigating various optimization techniques used in distributed GNN training. First, distributed GNN training is classified into several categories according to their workflows. In addition, their computational patterns and communication patterns, as well as the optimization techniques proposed by recent work are introduced. Second, the software frameworks and hardware platforms of distributed GNN training are also introduced for a deeper understanding. Third, distributed GNN training is compared with distributed training of deep neural networks, emphasizing the uniqueness of distributed GNN training. Finally, interesting issues and opportunities in this field are discussed.

Traditional machine learning follows a close-set assumption that the training and test set share the same label space. While in many practical scenarios, it is inevitable that some test samples belong to unknown classes (open-set). To fix this issue, Open-Set Recognition (OSR), whose goal is to make correct predictions on both close-set samples and open-set samples, has attracted rising attention. In this direction, the vast majority of literature focuses on the pattern of open-set samples. However, how to evaluate model performance in this challenging task is still unsolved. In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden's index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction. (2) Novelty detection AUC, which measures the ranking performance between close-set and open-set samples, ignores the close-set performance. To fix these issues, we propose a novel metric named OpenAUC. Compared with existing metrics, OpenAUC enjoys a concise pairwise formulation that evaluates open-set performance and close-set performance in a coupling manner. Further analysis shows that OpenAUC is free from the aforementioned inconsistency properties. Finally, an end-to-end learning method is proposed to minimize the OpenAUC risk, and the experimental results on popular benchmark datasets speak to its effectiveness.

近年来，已取得了巨大进展，以通过半监督学习（SSL）来纳入未标记的数据来克服效率低下的监督问题。大多数最先进的模型是基于对未标记的数据追求一致的模型预测的想法，该模型被称为输入噪声，这称为一致性正则化。尽管如此，对其成功的原因缺乏理论上的见解。为了弥合理论和实际结果之间的差距，我们在本文中提出了SSL的最坏情况一致性正则化技术。具体而言，我们首先提出了针对SSL的概括，该概括由分别在标记和未标记的训练数据上观察到的经验损失项组成。在这种界限的激励下，我们得出了一个SSL目标，该目标可最大程度地减少原始未标记的样本与其多重增强变体之间最大的不一致性。然后，我们提供了一种简单但有效的算法来解决提出的最小问题，从理论上证明它会收敛到固定点。五个流行基准数据集的实验验证了我们提出的方法的有效性。