用于对象检测的常规知识蒸馏（KD）方法主要集中于同质的教师学生探测器。但是，用于部署的轻质检测器的设计通常与高容量探测器显着不同。因此，我们研究了异构教师对之间的KD，以进行广泛的应用。我们观察到，异质KD（异核KD）的核心难度是由于不同优化的方式而导致异质探测器的主链特征之间的显着语义差距。常规的同质KD（HOMO-KD）方法遭受了这种差距的影响，并且很难直接获得异性KD的令人满意的性能。在本文中，我们提出了异助剂蒸馏（Head）框架，利用异质检测头作为助手来指导学生探测器的优化以减少此间隙。在头上，助手是一个额外的探测头，其建筑与学生骨干的老师负责人同质。因此，将异源KD转变为同性恋，从而可以从老师到学生的有效知识转移。此外，当训练有素的教师探测器不可用时，我们将头部扩展到一个无教师的头（TF-Head）框架。与当前检测KD方法相比，我们的方法已取得了显着改善。例如，在MS-COCO数据集上，TF-Head帮助R18视网膜实现33.9 MAP（+2.2），而Head将极限进一步推到36.2 MAP（+4.5）。

面部去夹旨在从模糊的输入图像恢复清晰的面部图像，具有更明确的结构和面部细节。然而，大多数传统的图像和面部去夹方法的重点是整个产生的图像分辨率，而不考虑特殊的面部纹理并且通常产生无充气的细节。考虑到面部和背景具有不同的分布信息，在本研究中，我们设计了一种基于可分离的归一化和自适应非规范化（SnAdnet）的有效面部去孔网络。首先，我们微调面部解析网络以获得精确的面部结构。然后，我们将脸部解析功能划分为面部前景和背景。此外，我们构建了一种新的特征自适应非规范化，以将FAYCIAL结构规则为辅助的条件，以产生更加和谐的面部结构。另外，我们提出了一种纹理提取器和多贴片鉴别器，以增强所生成的面部纹理信息。 Celeba和Celeba-HQ数据集的实验结果表明，所提出的面部去孔网络以更具面部细节恢复面部结构，并在结构相似性索引方法（SSIM），峰值信号方面对最先进的方法进行有利的方法。信噪比（PSNR），Frechet Inception距离（FID）和L1以及定性比较。

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even slightly boost the generalization performance. Theoretical understanding for such experimental observations are yet to be developed. This work makes the first attempt to study how different pruning fractions affect the model's gradient descent dynamics and generalization. Specifically, this work considers a classification task for overparameterized two-layer neural networks, where the network is randomly pruned according to different rates at the initialization. It is shown that as long as the pruning fraction is below a certain threshold, gradient descent can drive the training loss toward zero and the network exhibits good generalization performance. More surprisingly, the generalization bound gets better as the pruning fraction gets larger. To complement this positive result, this work further shows a negative result: there exists a large pruning fraction such that while gradient descent is still able to drive the training loss toward zero (by memorizing noise), the generalization performance is no better than random guessing. This further suggests that pruning can change the feature learning process, which leads to the performance drop of the pruned neural network. Up to our knowledge, this is the \textbf{first} generalization result for pruned neural networks, suggesting that pruning can improve the neural network's generalization.

Open Information Extraction (OIE) methods extract a large number of OIE triples (noun phrase, relation phrase, noun phrase) from text, which compose large Open Knowledge Bases (OKBs). However, noun phrases (NPs) and relation phrases (RPs) in OKBs are not canonicalized and often appear in different paraphrased textual variants, which leads to redundant and ambiguous facts. To address this problem, there are two related tasks: OKB canonicalization (i.e., convert NPs and RPs to canonicalized form) and OKB linking (i.e., link NPs and RPs with their corresponding entities and relations in a curated Knowledge Base (e.g., DBPedia). These two tasks are tightly coupled, and one task can benefit significantly from the other. However, they have been studied in isolation so far. In this paper, we explore the task of joint OKB canonicalization and linking for the first time, and propose a novel framework JOCL based on factor graph model to make them reinforce each other. JOCL is flexible enough to combine different signals from both tasks, and able to extend to fit any new signals. A thorough experimental study over two large scale OIE triple data sets shows that our framework outperforms all the baseline methods for the task of OKB canonicalization (OKB linking) in terms of average F1 (accuracy).

This paper is about an extraordinary phenomenon. Suppose we don't use any low-light images as training data, can we enhance a low-light image by deep learning? Obviously, current methods cannot do this, since deep neural networks require to train their scads of parameters using copious amounts of training data, especially task-related data. In this paper, we show that in the context of fundamental deep learning, it is possible to enhance a low-light image without any task-related training data. Technically, we propose a new, magical, effective and efficient method, termed \underline{Noi}se \underline{SE}lf-\underline{R}egression (NoiSER), which learns a gray-world mapping from Gaussian distribution for low-light image enhancement (LLIE). Specifically, a self-regression model is built as a carrier to learn a gray-world mapping during training, which is performed by simply iteratively feeding random noise. During inference, a low-light image is directly fed into the learned mapping to yield a normal-light one. Extensive experiments show that our NoiSER is highly competitive to current task-related data based LLIE models in terms of quantitative and visual results, while outperforming them in terms of the number of parameters, training time and inference speed. With only about 1K parameters, NoiSER realizes about 1 minute for training and 1.2 ms for inference with 600$\times$400 resolution on RTX 2080 Ti. Besides, NoiSER has an inborn automated exposure suppression capability and can automatically adjust too bright or too dark, without additional manipulations.

Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a task-based information gap to decrease the performance, since the object features in detection task are suboptimal representation and cannot provide all necessary information for subsequent text generation. Besides, object features are usually represented by the last layer features that lose the local details of input images. In this paper, we propose a novel One-Stage Image Captioner (OSIC) with dynamic multi-sight learning, which directly transforms input image into descriptive sentences in one stage. As a result, the task-based information gap can be greatly reduced. To obtain rich features, we use the Swin Transformer to calculate multi-level features, and then feed them into a novel dynamic multi-sight embedding module to exploit both global structure and local texture of input images. To enhance the global modeling of encoder for caption, we propose a new dual-dimensional refining module to non-locally model the interaction of the embedded features. Finally, OSIC can obtain rich and useful information to improve the image caption task. Extensive comparisons on benchmark MS-COCO dataset verified the superior performance of our method.

尽管视觉问题答案取得了长足的进步（VQA），但当前的VQA模型严重依赖问题类型及其相应的频繁答案（即语言先验）之间的表面相关性来做出预测，而无需真正理解输入。在这项工作中，我们用相同的问题类型定义了培训实例，但与\ textit {表面上相似的实例}定义了不同的答案，并将语言先验归因于VQA模型在此类情况下的混淆。为了解决这个问题，我们提出了一个新颖的培训框架，该培训框架明确鼓励VQA模型区分表面上相似的实例。具体而言，对于每个培训实例，我们首先构建一个包含其表面上相似的对应物的集合。然后，我们利用所提出的区分模块增加了答案空间中实例及其对应物之间的距离。这样，VQA模型被迫进一步关注问题类型的输入的其他部分，这有助于克服语言先验。实验结果表明，我们的方法在VQA-CP V2上实现了最新性能。代码可在\ href {https://github.com/wyk-nku/distinguishing-vqa.git} {sickithing-vqa}中获得。

视频亮点检测长期以来一直是计算机视觉任务中的主题，挖掘出未接触的原始视频输入的用户出现剪辑。但是，在大多数情况下，这一研究中的主流方法建立在封闭的世界假设上，在封闭的世界假设中，固定数量的突出显示类别是提前正确定义的，并且需要同时可用的所有培训数据，并且作为一个结果，相对于突出显示类别和数据集大小的可伸缩性差。为了解决上面提到的问题，我们提出了一个视频突出显示检测器，能够逐步学习，即\ textbf {g} lobal \ textbf {p} rototype \ textbf {e} ncoding（gpe），捕获新定义的视频亮点。通过其相应的原型扩展数据集。除此之外，我们提供了一个注释且昂贵的数据集，称为\ emph {Bytefood}，包括超过5.1k的美食视频属于\ emph {cooke}，\ emph {eat}，\ emph {food Material}，\ emph {cooke}，和\ emph {演示}。据我们所知，这是第一次将增量学习设置引入视频突出显示检测，从而减轻培训视频输入的负担，并促进了按数据集的大小成比例的传统神经网络的可扩展性和域的数量。此外，所提出的GPE超过了\ emph {Bytefood}上的当前增量学习方法，至少报告了1.57 \％MAP的改善。代码和数据集将更早提供。

插槽填充和意图检测是自然语言理解领域的两个基本任务。由于这两项任务之间存在很强的相关性，因此以前的研究努力通过多任务学习或设计功能交互模块来建模它们，以提高每个任务的性能。但是，现有的方法都没有考虑句子的结构信息与两个任务的标签语义之间的相关性。话语的意图和语义成分取决于句子的句法元素。在本文中，我们研究了一个多透明的标签改进网络，该网络利用依赖性结构和标签语义嵌入。考虑到增强句法表示，我们将句子的依赖性结构介绍到我们的模型中。为了捕获句法信息和任务标签之间的语义依赖性，我们将特定于任务的特征与相应的标签嵌入通过注意机制相结合。实验结果表明，我们的模型在两个公共数据集上实现了竞争性能。

时间动作本地化旨在预测未修剪长视频中每个动作实例的边界和类别。基于锚或建议的大多数先前方法忽略了整个视频序列中的全局本地上下文相互作用。此外，他们的多阶段设计无法直接生成动作边界和类别。为了解决上述问题，本文提出了一种新颖的端到端模型，称为自适应感知变压器（简称apperformer）。具体而言，Adaperformer探索了双支球多头的自我发项机制。一个分支会照顾全球感知的关注，该注意力可以模拟整个视频序列并汇总全球相关环境。而其他分支集中于局部卷积转移，以通过我们的双向移动操作来汇总框架内和框架间信息。端到端性质在没有额外步骤的情况下产生视频动作的边界和类别。提供了广泛的实验以及消融研究，以揭示我们设计的有效性。我们的方法在Thumos14数据集上实现了最先进的准确性（根据map@0.5、42.6 \％map@0.7和62.7 \％map@avg），并在活动网络上获得竞争性能， -1.3数据集，平均地图为36.1 \％。代码和型号可在https://github.com/soupero/adaperformer上找到。