视觉表示学习是解决各种视力问题的关键。依靠开创性的网格结构先验，卷积神经网络（CNN）已成为大多数深视觉模型的事实上的标准架构。例如，经典的语义分割方法通常采用带有编码器编码器体系结构的完全横向卷积网络（FCN）。编码器逐渐减少了空间分辨率，并通过更大的接受场来学习更多抽象的视觉概念。由于上下文建模对于分割至关重要，因此最新的努力一直集中在通过扩张（即极度）卷积或插入注意力模块来增加接受场。但是，基于FCN的体系结构保持不变。在本文中，我们旨在通过将视觉表示学习作为序列到序列预测任务来提供替代观点。具体而言，我们部署纯变压器以将图像编码为一系列贴片，而无需局部卷积和分辨率减少。通过在变压器的每一层中建立的全球环境，可以学习更强大的视觉表示形式，以更好地解决视力任务。特别是，我们的细分模型（称为分割变压器（SETR））在ADE20K上擅长（50.28％MIOU，这是提交当天测试排行榜中的第一个位置），Pascal环境（55.83％MIOU），并在CityScapes上达到竞争成果。此外，我们制定了一个分层局部全球（HLG）变压器的家族，其特征是窗户内的本地关注和跨窗户的全球性专注于层次结构和金字塔架构。广泛的实验表明，我们的方法在各种视觉识别任务（例如，图像分类，对象检测和实例分割和语义分割）上实现了吸引力的性能。

视觉变形金刚（VIT）通过贴片图像令牌化推动了各种视觉识别任务的最先进，然后是堆叠的自我注意操作。采用自我发场模块会导致计算和内存使用情况的二次复杂性。因此，已经在自然语言处理中进行了各种尝试以线性复杂性近似自我发挥计算的尝试。但是，这项工作的深入分析表明，它们在理论上是缺陷的，或者在经验上是无效的视觉识别。我们确定它们的局限性植根于在近似过程中保留软马克斯的自我注意力。具体而言，传统的自我注意力是通过使令状特征向量之间的缩放点产物标准化来计算的。保留SoftMax操作会挑战任何随后的线性化工作。在这个见解下，首次提出了无软磁变压器（缩写为软的变压器）。为了消除自我注意事项的软马克斯操作员，采用高斯内核函数来替代点产品相似性。这使完整的自发矩阵可以通过低级矩阵分解近似。我们近似的鲁棒性是通过使用牛顿 - 拉夫森方法来计算其摩尔 - 芬罗逆的。此外，在低级别的自我注意事项上引入了有效的对称归一化，以增强模型的推广性和可传递性。对Imagenet，Coco和ADE20K的广泛实验表明，我们的软可以显着提高现有VIT变体的计算效率。至关重要的是，具有线性复杂性，允许使用较长的令牌序列，从而使精度和复杂性之间的权衡较高。

我们提出了用于自我监督的视觉表示学习的变换不变性和协方差对比度（TICO）。与其他最新的自我监督学习方法类似，我们的方法基于同一图像的不同变形版本之间的嵌入之间的一致性，这推动了编码器产生变换不变表示。为了避免编码器生成恒定向量的微不足道解，我们通过惩罚低等级解决方案将嵌入的嵌入的协方差矩阵正常化。通过共同最大程度地减少变换不变性损失和协方差对比损失，我们得到了一个能够为下游任务产生有用表示的编码器。我们分析了我们的方法，并表明它可以被视为MOCO的变体，具有无限尺寸的隐式存储器库，无需额外的内存成本。这使我们的方法在使用小批量尺寸时的性能要比替代方法更好。 TICO也可以看作是Barlow双胞胎的修改。通过将对比度和冗余方法联系起来，TICO为我们提供了有关关节嵌入方法如何工作的新见解。

自我监督的学习表现出优于各种视觉基准的监督方法。暹罗网络鼓励嵌入是扭曲的不变，是最成功的自我观察的视觉表示学习方法之一。在所有增强方法中，掩盖是最通用，最直接的方法，它有可能应用于各种输入，并且需要最少的域知识。但是，蒙面的暹罗网络需要特殊的归纳偏见，并且实际上仅与视觉变压器配合得很好。这项工作从经验上研究了用Convnets掩盖暹罗网络背后的问题。我们提出了几种经验设计，以逐渐克服这些问题。我们的方法在低射击图像分类方面竞争性能，并且优于对象检测基准测试的先前方法。我们讨论了剩余的几个问题，希望这项工作可以为未来的通用自我监督学习提供有用的数据点。

一个自动驾驶感知模型旨在将3D语义表示从多个相机集体提取到自我汽车的鸟类视图（BEV）坐标框架中，以使下游规划师接地。现有的感知方法通常依赖于整个场景的容易出错的深度估计，或者学习稀疏的虚拟3D表示没有目标几何结构，这两者在性能和/或能力上仍然有限。在本文中，我们介绍了一种新颖的端到端体系结构，用于自我3D表示从任意数量的无限摄像机视图中学习。受射线追踪原理的启发，我们将“想象眼睛”的两极分化网格设计为可学习的自我3D表示，并通过适应性注意机制与3D到2D投影一起以自适应注意机制的形式制定学习过程。至关重要的是，该公式允许从2D图像中提取丰富的3D表示，而无需任何深度监督，并且内置的几何结构一致W.R.T. bev。尽管具有简单性和多功能性，但对标准BEV视觉任务（例如，基于摄像机的3D对象检测和BEV细分）进行了广泛的实验表明，我们的模型的表现均优于所有最新替代方案，从多任务学习。

为了在商店中充分利用计算机视觉技术，需要考虑适合零售场景特征的实际需求。为了实现这一目标，我们介绍了联合零售数据集（Unitail），这是针对检测，阅读和匹配算法的产品的基本视觉任务的大规模基准。凭借注释的180万个四边形实例，该Unitail提供了一个检测数据集，以更好地对齐产品外观。此外，它提供了一个包含1454个产品类别，30k文本区域和21k转录的画廊风格的OCR数据集，以实现对产品的强大阅读并激励增强的产品匹配。除了使用各种最新技术对数据集进行基准测试外，我们还定制了一个新的检测器以进行产品检测，并提供了一个简单的基于OCR的匹配解决方案，以验证其有效性。

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoderdecoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (i.e., without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.

A crucial issue of current text generation models is that they often uncontrollably generate factually inconsistent text with respective of their inputs. Limited by the lack of annotated data, existing works in evaluating factual consistency directly transfer the reasoning ability of models trained on other data-rich upstream tasks like question answering (QA) and natural language inference (NLI) without any further adaptation. As a result, they perform poorly on the real generated text and are biased heavily by their single-source upstream tasks. To alleviate this problem, we propose a weakly supervised framework that aggregates multiple resources to train a precise and efficient factual metric, namely WeCheck. WeCheck first utilizes a generative model to accurately label a real generated sample by aggregating its weak labels, which are inferred from multiple resources. Then, we train the target metric model with the weak supervision while taking noises into consideration. Comprehensive experiments on a variety of tasks demonstrate the strong performance of WeCheck, which achieves a 3.4\% absolute improvement over previous state-of-the-art methods on TRUE benchmark on average.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Recent advances in operator learning theory have improved our knowledge about learning maps between infinite dimensional spaces. However, for large-scale engineering problems such as concurrent multiscale simulation for mechanical properties, the training cost for the current operator learning methods is very high. The article presents a thorough analysis on the mathematical underpinnings of the operator learning paradigm and proposes a kernel learning method that maps between function spaces. We first provide a survey of modern kernel and operator learning theory, as well as discuss recent results and open problems. From there, the article presents an algorithm to how we can analytically approximate the piecewise constant functions on R for operator learning. This implies the potential feasibility of success of neural operators on clustered functions. Finally, a k-means clustered domain on the basis of a mechanistic response is considered and the Lippmann-Schwinger equation for micro-mechanical homogenization is solved. The article briefly discusses the mathematics of previous kernel learning methods and some preliminary results with those methods. The proposed kernel operator learning method uses graph kernel networks to come up with a mechanistic reduced order method for multiscale homogenization.