In-context learning, as a new paradigm in NLP, allows the model to rapidly adapt to various tasks with only a handful of prompts and examples. But in computer vision, the difficulties for in-context learning lie in that tasks vary significantly in the output representations, thus it is unclear how to define the general-purpose task prompts that the vision model can understand and transfer to out-of-domain tasks. In this work, we present Painter, a generalist model which addresses these obstacles with an "image"-centric solution, that is, to redefine the output of core vision tasks as images, and specify task prompts as also images. With this idea, our training process is extremely simple, which performs standard masked image modeling on the stitch of input and output image pairs. This makes the model capable of performing tasks conditioned on visible image patches. Thus, during inference, we can adopt a pair of input and output images from the same task as the input condition, to indicate which task to perform. Without bells and whistles, our generalist Painter can achieve competitive performance compared to well-established task-specific models, on seven representative vision tasks ranging from high-level visual understanding to low-level image processing. Painter significantly outperforms recent generalist models on several challenging tasks. Surprisingly, our model shows capabilities of completing out-of-domain tasks, which do not exist in the training data, such as open-category keypoint detection and object segmentation, validating the powerful task transferability of in-context learning.

Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain. However, only by tackling the performance gap above can we fully exploit the practical value of web datasets. To this end, we propose a Few-shot guided Prototypical (FoPro) representation learning method, which only needs a few labeled examples from reality and can significantly improve the performance in the real-world domain. Specifically, we initialize each class center with few-shot real-world data as the ``realistic" prototype. Then, the intra-class distance between web instances and ``realistic" prototypes is narrowed by contrastive learning. Finally, we measure image-prototype distance with a learnable metric. Prototypes are polished by adjacent high-quality web images and involved in removing distant out-of-distribution samples. In experiments, FoPro is trained on web datasets with a few real-world examples guided and evaluated on real-world datasets. Our method achieves the state-of-the-art performance on three fine-grained datasets and two large-scale datasets. Compared with existing WSL methods under the same few-shot settings, FoPro still excels in real-world generalization. Code is available at https://github.com/yuleiqin/fopro.

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms. Source code and data will be released at https://github.com/JiawangBian/sc_depth_pl

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone on the ADE20K dataset and achieves new state-of-the-art performance on COCO-Stuff-10K and PASCAL-Context datasets. Furthermore, to reduce the computational cost of the ViT backbone, we propose query-based down-sampling (QD) and query-based up-sampling (QU) to build a Shrunk structure. With the proposed Shrunk structure, the model can save up to $40\%$ computations while maintaining competitive performance.

视频和文本之间的跨模式检索因网络上的视频迅速出现而越来越多。通常，视频包含丰富的实例和事件信息，查询文本仅描述了信息的一部分。因此，视频可以对应于多个不同的文本说明和查询。我们将此现象称为``视频文本对应歧义''问题。当前技术主要集中于挖掘视频和文本内容之间的本地或多级对齐（\ textit {e.g。}，对实体和动词的动作对象）。这些方法很难通过仅使用一个单个功能来描述视频来减轻视频文本的歧义，这需要同时与多个不同的文本功能匹配。为了解决这个问题，我们提出了一个文本自适应多个视觉原型匹配模型，该模型会自动捕获多个原型，以通过自适应聚合视频令牌功能来描述视频。给定查询文本，相似性由最相似的原型确定，以在视频中找到对应关系，该视频称为文本自适应匹配。为了学习代表视频中丰富信息的多种原型，我们提出了差异损失，以鼓励不同的原型参与视频的不同内容。我们的方法在四个公共视频检索数据集上优于最先进的方法。

我们研究了可靠的功能表示的任务，旨在在多个数据集上良好地概括以进行行动识别。我们建立了有关变形金刚的功效的方法。尽管在过去的十年中，我们目睹了视频动作识别的巨大进展，但如何培训单个模型可以在多个数据集中表现良好的单一模型仍然充满挑战而有价值。在这里，我们提出了一种新颖的多数据集训练范式，Multitrain，设计了两个新的损失条款，即信息丰富的损失和投射损失，旨在学习稳健的表现以进行行动识别。特别是，信息性损失最大化了功能嵌入的表现力，而每个数据集的投影损失遍历了数据集的类之间的内在关系。我们验证方法对五个具有挑战性的数据集的有效性，即动力学400，动力学700，矩矩，活动网络和某种效果 - v2数据集。广泛的实验结果表明，我们的方法可以始终如一地提高最新性能。

尽管在过去几年中取得了重大进展，但使用单眼图像进行深度估计仍然存在挑战。首先，训练度量深度预测模型的训练是不算气的，该预测模型可以很好地推广到主要由于训练数据有限的不同场景。因此，研究人员建立了大规模的相对深度数据集，这些数据集更容易收集。但是，由于使用相对深度数据训练引起的深度转移，现有的相对深度估计模型通常无法恢复准确的3D场景形状。我们在此处解决此问题，并尝试通过对大规模相对深度数据进行训练并估算深度转移来估计现场形状。为此，我们提出了一个两阶段的框架，该框架首先将深度预测到未知量表并从单眼图像转移，然后利用3D点云数据来预测深度​​移位和相机的焦距，使我们能够恢复恢复3D场景形状。由于两个模块是单独训练的，因此我们不需要严格配对的培训数据。此外，我们提出了图像级的归一化回归损失和基于正常的几何损失，以通过相对深度注释来改善训练。我们在九个看不见的数据集上测试我们的深度模型，并在零拍摄评估上实现最先进的性能。代码可用：https：//git.io/depth

在过去的几年中，使用机器学习的编程语言处理（PLP）取得了广泛的改进。越来越多的人有兴趣探索这个有前途的领域。但是，对于新的研究人员和开发人员来说，要找到合适的组件来构建自己的机器学习管道，鉴于要解决的多样化的PLP任务，已发布大量数据集和模型，以及一组复杂的编译器或工具。涉及。为了改善机器学习组件的可发现性，可访问性，互操作性和可重复性（公平性），我们在基于机器学习的PLP领域中收集和分析了一组代表性论文。然后，我们确定并表征关键概念，包括PLP任务，模型架构和支持工具。最后，我们展示了一些利用可重复使用的组件来构建机器学习管道以解决一组PLP任务的例子。

现有的深度完成方法通常以特定的稀疏深度类型为目标，并且在任务域之间概括较差。我们提出了一种方法，可以通过各种范围传感器（包括现代手机中的范围传感器或多视图重建算法）获得稀疏/半密度，嘈杂和潜在的低分辨率深度图。我们的方法利用了在大规模数据集中训练的单个图像深度预测网络的形式的数据驱动的先验，其输出被用作我们模型的输入。我们提出了一个有效的培训计划，我们在典型的任务域中模拟各种稀疏模式。此外，我们设计了两个新的基准测试，以评估深度完成方法的普遍性和鲁棒性。我们的简单方法显示了针对最先进的深度完成方法的优越的跨域泛化能力，从而引入了一种实用的解决方案，以在移动设备上捕获高质量的深度捕获。代码可在以下网址获得：https：//github.com/yvanyin/filldepth。

视频文本发现（VTS）是需要同时检测，跟踪和识别视频中文本的任务。现有的视频文本发现方法通常开发复杂的管道和多个模型，这不是实时应用程序的朋友。在这里，我们提出了一个带有对比表示学习（Cotext）的实时端到端视频文本检测器。我们的贡献分为三个：1）Cotext同时解决实时端到端可训练框架中的三个任务（例如，文本检测，跟踪，识别）。 2）通过对比度学习，Cotext模拟了多个帧的长距离依赖性和学习时间信息。 3）简单，轻巧的体系结构设计用于有效和准确的性能，包括带有蒙版ROI的基于CTC的GPU - 平行检测后处理。广泛的实验显示了我们方法的优越性。尤其是，Cotext在ICDAR2015VIDEO上以41.0 fps的速度实现了一个视频文本，以72.0％的IDF1命中，其video的范围为10.5％和32.0 fps，改进了先前的最佳方法。该代码可以在github.com/weijiawu/cotext上找到。