在Imagenet或其他大规模数据数据上的预培训模型导致计算机愿景的主要进步，尽管伴随着与策划成本，隐私，使用权和道德问题相关的缺点。在本文中，我们首次研究了基于由图形模拟器生成的合成数据到来自非常不同的域的下游任务的培训模型的可转换性。在使用此类合成数据进行预培训时，我们发现不同任务的下游性能受到不同配置的不同配置（例如，照明，对象姿势，背景等），并且没有单尺寸适合 - 所有解决方案。因此，更好地将合成的预训练数据量身定制到特定的下游任务，以获得最佳性能。我们介绍Task2SIM，一个统一的模型将下游任务表示映射到最佳模拟参数，以为它们生成合成的预训练数据。 Task2SIM通过培训学习此映射，以查找一组“看到”任务上的最佳参数集。曾经训练过，它可以用于预测一个新颖的“看不见”任务的最佳仿真参数，而无需额外的培训。鉴于每级图像数量的预算，我们具有20个不同的下游任务的广泛实验，显示了Task2SIM的任务 - 自适应预训练数据导致明显更好的下游性能，而不是在看见和看不见的任务上的非自适应选择模拟参数。它甚至是竞争对手的真实图像的竞争力。

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.

神经网络分类器已成为当前“火车前的Fine-Tune”范例的De-Facto选择。在本文中，我们调查了K $ -Nearest邻居（K-NN）分类器，这是一种从预先学习时代的无古典无模型学习方法，作为基于现代神经网络的方法的增强。作为懒惰的学习方法，K-Nn简单地聚集了训练集中的测试图像和顶-k邻居之间的距离。我们采用k-nn具有由监督或自我监督方法产生的预训练的视觉表现，分为两个步骤：（1）利用K-NN预测概率作为培训期间容易\〜〜硬示例的迹象。 （2）用增强分类器的预测分布线性地插入k-nn。通过广泛的实验在广泛的分类任务中，我们的研究揭示了K-NN集成与额外见解的一般性和灵活性：（1）K-NN实现竞争结果，有时甚至优于标准的线性分类器。 （2）结合K-NN对参数分类器执行不良和/或低数据制度的任务特别有益。我们希望这些发现将鼓励人们重新考虑预先学习的角色，计算机愿景中的古典方法。我们的代码可用于：https：//github.com/kmnp/nn-revisit。

Deep transfer learning has been widely used for knowledge transmission in recent years. The standard approach of pre-training and subsequently fine-tuning, or linear probing, has shown itself to be effective in many down-stream tasks. Therefore, a challenging and ongoing question arises: how to quantify cross-task transferability that is compatible with transferred results while keeping self-consistency? Existing transferability metrics are estimated on the particular model by conversing source and target tasks. They must be recalculated with all existing source tasks whenever a novel unknown target task is encountered, which is extremely computationally expensive. In this work, we highlight what properties should be satisfied and evaluate existing metrics in light of these characteristics. Building upon this, we propose Principal Gradient Expectation (PGE), a simple yet effective method for assessing transferability across tasks. Specifically, we use a restart scheme to calculate every batch gradient over each weight unit more than once, and then we take the average of all the gradients to get the expectation. Thus, the transferability between the source and target task is estimated by computing the distance of normalized principal gradients. Extensive experiments show that the proposed transferability metric is more stable, reliable and efficient than SOTA methods.

Computational pathology can lead to saving human lives, but models are annotation hungry and pathology images are notoriously expensive to annotate. Self-supervised learning has shown to be an effective method for utilizing unlabeled data, and its application to pathology could greatly benefit its downstream tasks. Yet, there are no principled studies that compare SSL methods and discuss how to adapt them for pathology. To address this need, we execute the largest-scale study of SSL pre-training on pathology image data, to date. Our study is conducted using 4 representative SSL methods on diverse downstream tasks. We establish that large-scale domain-aligned pre-training in pathology consistently out-performs ImageNet pre-training in standard SSL settings such as linear and fine-tuning evaluations, as well as in low-label regimes. Moreover, we propose a set of domain-specific techniques that we experimentally show leads to a performance boost. Lastly, for the first time, we apply SSL to the challenging task of nuclei instance segmentation and show large and consistent performance improvements under diverse settings.

培训计算机视觉模型通常需要在各种场景配置和属性集中收集和标记大量图像。这个过程非常耗时，并且要确保捕获的数据分布映射到应用程序方案的目标域，这是一项挑战。最近，综合数据已成为解决这两个问题的一种方式。但是，现有方法要么要求人类专家手动调整每个场景属性，要么使用几乎无法控制的自动方法；这需要渲染大量的随机数据变化，这很慢，对于目标域通常是次优的。我们介绍了第一个完全可区分的合成数据管道，该数据管道使用具有目标应用程序损耗函数的闭环中的神经辐射场（NERF）。我们的方法可以在没有人工的情况下生成数据，以最大程度地提高目标任务的准确性。我们说明了我们方法对合成和现实对象检测任务的有效性。我们还引入了一个新的“ YCB野外”数据集和基准标准，该数据集和基准为对象检测提供了一种在现实世界环境中具有多种姿势的测试方案。

Intermediate features of a pre-trained model have been shown informative for making accurate predictions on downstream tasks, even if the model backbone is kept frozen. The key challenge is how to utilize these intermediate features given their gigantic amount. We propose visual query tuning (VQT), a simple yet effective approach to aggregate intermediate features of Vision Transformers. Through introducing a handful of learnable ``query'' tokens to each layer, VQT leverages the inner workings of Transformers to ``summarize'' rich intermediate features of each layer, which can then be used to train the prediction heads of downstream tasks. As VQT keeps the intermediate features intact and only learns to combine them, it enjoys memory efficiency in training, compared to many other parameter-efficient fine-tuning approaches that learn to adapt features and need back-propagation through the entire backbone. This also suggests the complementary role between VQT and those approaches in transfer learning. Empirically, VQT consistently surpasses the state-of-the-art approach that utilizes intermediate features for transfer learning and outperforms full fine-tuning in many cases. Compared to parameter-efficient approaches that adapt features, VQT achieves much higher accuracy under memory constraints. Most importantly, VQT is compatible with these approaches to attain even higher accuracy, making it a simple add-on to further boost transfer learning.

近年来，人员检测和人类姿势估计已经取得了很大的进步，通过大规模标记的数据集帮助。但是，这些数据集没有保证或分析人类活动，姿势或情境多样性。此外，隐私，法律，安全和道德问题可能会限制收集更多人类数据的能力。一个新兴的替代方案，用于减轻这些问题的一些问题是合成数据。然而，综合数据生成器的创建令人难以置信的具有挑战性，并防止研究人员探索他们的实用性。因此，我们释放了一个以人为本的合成数据发生器PeoplesAnspeople，它包含模拟就绪3D人类资产，参数化照明和相机系统，并生成2D和3D边界框，实例和语义分段，以及Coco姿态标签。使用PeoplesAnspeople，我们使用Detectron2 KeyPoint R-CNN变体进行基准合成数据训练[1]。我们发现，使用合成数据进行预培训网络和对目标现实世界数据的微调（几次传输到Coco-Person Rain的有限子集[2]）导致了60.37 $ 60.37 $的关键点AP（ Coco Test-Dev2017）使用相同的实际数据培训的型号优于同一实际数据（35.80美元的Keypoint AP），并使用Imagenet预先培训（Keypoint AP为57.50美元）。这种自由可用的数据发生器应使其在人用于人工以人为主的计算机视野中的临界领域进行实际转移学习的新兴仿真领域。

我们提出了一个统一的查看，即通过通用表示，一个深层神经网络共同学习多个视觉任务和视觉域。同时学习多个问题涉及最大程度地减少具有不同幅度和特征的多个损失函数的加权总和，从而导致一个损失的不平衡状态，与学习每个问题的单独模型相比，一个损失的不平衡状态主导了优化和差的结果。为此，我们提出了通过小容量适配器将多个任务/特定于域网络的知识提炼到单个深神经网络中的知识。我们严格地表明，通用表示在学习NYU-V2和CityScapes中多个密集的预测问题方面实现了最新的表现，来自视觉Decathlon数据集中的不同域中的多个图像分类问题以及MetadataSet中的跨域中的几个域中学习。最后，我们还通过消融和定性研究进行多次分析。

大规模数据集的预培训模型，如想象成，是计算机视觉中的标准实践。此范例对于具有小型培训套的任务特别有效，其中高容量模型往往会过度装备。在这项工作中，我们考虑一个自我监督的预训练场景，只能利用目标任务数据。我们考虑数据集，如斯坦福汽车，草图或可可，这是比想象成小的数量的顺序。我们的研究表明，在本文中介绍的Beit或诸如Beit或Variant的去噪对预训练数据的类型和大小比通过比较图像嵌入来训练的流行自我监督方法更加强大。我们获得了竞争性能与ImageNet预训练相比，来自不同域的各种分类数据集。在Coco上，当专注于使用Coco Images进行预训练时，检测和实例分割性能超过了可比设置中的监督Imagenet预训练。

Jitendra Malik once said, "Supervision is the opium of the AI researcher". Most deep learning techniques heavily rely on extreme amounts of human labels to work effectively. In today's world, the rate of data creation greatly surpasses the rate of data annotation. Full reliance on human annotations is just a temporary means to solve current closed problems in AI. In reality, only a tiny fraction of data is annotated. Annotation Efficient Learning (AEL) is a study of algorithms to train models effectively with fewer annotations. To thrive in AEL environments, we need deep learning techniques that rely less on manual annotations (e.g., image, bounding-box, and per-pixel labels), but learn useful information from unlabeled data. In this thesis, we explore five different techniques for handling AEL.

Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models on simulated images that transfer to real images by randomizing rendering in the simulator. With enough variability in the simulator, the real world may appear to the model as just another variation. We focus on the task of object localization, which is a stepping stone to general robotic manipulation skills. We find that it is possible to train a real-world object detector that is accurate to 1.5 cm and robust to distractors and partial occlusions using only data from a simulator with non-realistic random textures. To demonstrate the capabilities of our detectors, we show they can be used to perform grasping in a cluttered environment. To our knowledge, this is the first successful transfer of a deep neural network trained only on simulated RGB images (without pre-training on real images) to the real world for the purpose of robotic control.

对分布（OOD）数据的概括是人类自然的能力，但对于机器而言挑战。这是因为大多数学习算法强烈依赖于i.i.d.〜对源/目标数据的假设，这在域转移导致的实践中通常会违反。域的概括（DG）旨在通过仅使用源数据进行模型学习来实现OOD的概括。在过去的十年中，DG的研究取得了长足的进步，导致了广泛的方法论，例如，基于域的一致性，元学习，数据增强或合奏学习的方法，仅举几例；还在各个应用领域进行了研究，包括计算机视觉，语音识别，自然语言处理，医学成像和强化学习。在本文中，首次提供了DG中的全面文献综述，以总结过去十年来的发展。具体而言，我们首先通过正式定义DG并将其与其他相关领域（如域适应和转移学习）联系起来来涵盖背景。然后，我们对现有方法和理论进行了彻底的审查。最后，我们通过有关未来研究方向的见解和讨论来总结这项调查。

我们建议使用实例检测（实例检测）的新方法，合成优化的布局，以预处理对象检测器具有合成图像。我们的“固体”方法由两个主要组成部分组成：（1）使用具有优化场景布置的未标记的3D模型生成合成图像；（2）在“实例检测”任务上预修对象检测器 - 给定描绘对象的查询图像，检测目标图像中完全相同对象的所有实例。我们的方法不需要任何语义标签来进行预处理，并允许使用任意，不同的3D模型。对可可的实验表明，通过优化的数据生成和适当的预处理任务，合成数据可以是预处理对象探测器的高效数据。特别是，对渲染图像进行预修会在实际图像上预处理，同时使用明显较少的计算资源，从而实现了性能竞争。代码可在https://github.com/princeton-vl/solid上找到。

视觉变压器（VIT）已被证明可以在广泛的视觉应用中获得高度竞争性的性能，例如图像分类，对象检测和语义图像分割。与卷积神经网络相比，通常发现视觉变压器的较弱的电感偏差会在较小的培训数据集上培训时，会增加对模型正则化或数据增强的依赖（简称为“ AUGREG”）。我们进行了一项系统的实证研究，以便更好地了解培训数据，AUGREG，模型大小和计算预算之间的相互作用。作为这项研究的一个结果，我们发现增加的计算和AUGREG的组合可以产生与在数量级上训练的模型相同的训练数据的模型：我们在公共Imagenet-21K数据集中培训各种尺寸的VIT模型在较大的JFT-300M数据集上匹配或超越其对手的培训。

Few-shot learning aims to fast adapt a deep model from a few examples. While pre-training and meta-training can create deep models powerful for few-shot generalization, we find that pre-training and meta-training focuses respectively on cross-domain transferability and cross-task transferability, which restricts their data efficiency in the entangled settings of domain shift and task shift. We thus propose the Omni-Training framework to seamlessly bridge pre-training and meta-training for data-efficient few-shot learning. Our first contribution is a tri-flow Omni-Net architecture. Besides the joint representation flow, Omni-Net introduces two parallel flows for pre-training and meta-training, responsible for improving domain transferability and task transferability respectively. Omni-Net further coordinates the parallel flows by routing their representations via the joint-flow, enabling knowledge transfer across flows. Our second contribution is the Omni-Loss, which introduces a self-distillation strategy separately on the pre-training and meta-training objectives for boosting knowledge transfer throughout different training stages. Omni-Training is a general framework to accommodate many existing algorithms. Evaluations justify that our single framework consistently and clearly outperforms the individual state-of-the-art methods on both cross-task and cross-domain settings in a variety of classification, regression and reinforcement learning problems.

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (e.g., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has been instrumental to many applications in language and vision. Yet, very little is known about its usefulness in 3D point cloud understanding. We see this as an opportunity considering the effort required for annotating data in 3D. In this work, we aim at facilitating research on 3D representation learning. Different from previous works, we focus on high-level scene understanding tasks. To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes. Our findings are extremely encouraging: using a unified triplet of architecture, source dataset, and contrastive loss for pre-training, we achieve improvement over recent best results in segmentation and detection across 6 different benchmarks for indoor and outdoor, real and synthetic datasets -demonstrating that the learned representation can generalize across domains. Furthermore, the improvement was similar to supervised pre-training, suggesting that future efforts should favor scaling data collection over more detailed annotation. We hope these findings will encourage more research on unsupervised pretext task design for 3D deep learning. Our code is publicly available at https://github.com/facebookresearch/PointContrast

从自然语言监督中学习视觉表示，最近在许多开创性的作品中表现出了巨大的希望。通常，这些具有语言的视觉模型表现出对各种数据集和任务的强大可传递性。但是，由于缺乏易于使用的评估工具包和公共基准，评估这些模型的可转让性仍然很具有挑战性。为了解决这个问题，我们构建了高级版（评估语言的视觉任务级传输），这是用于评估（预训练）语言增强视觉模型的第一个基准和工具包。升华由三个组成部分组成。 （i）数据集。作为下游评估套件，它由20个图像分类数据集和35个对象检测数据集组成，每个数据集都用外部知识来增强。 （ii）工具包。开发了自动高参数调谐工具包，以促进下游任务的模型评估。 （iii）指标。多种评估指标用于测量样品效率（零射击和少量）和参数效率（线性探测和完整模型微调）。我们在https://computer-vision-in-the-wild.github.io/elevater/上公开发布leverater

Recent large-scale image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a very simple text prompt. Could such models render real images obsolete for training image prediction models? In this paper, we answer part of this provocative question by questioning the need for real images when training models for ImageNet classification. More precisely, provided only with the class names that have been used to build the dataset, we explore the ability of Stable Diffusion to generate synthetic clones of ImageNet and measure how useful they are for training classification models from scratch. We show that with minimal and class-agnostic prompt engineering those ImageNet clones we denote as ImageNet-SD are able to close a large part of the gap between models produced by synthetic images and models trained with real images for the several standard classification benchmarks that we consider in this study. More importantly, we show that models trained on synthetic images exhibit strong generalization properties and perform on par with models trained on real data.

现代计算机视觉系统中使用的深度神经网络需要巨大的图像数据集来训练它们。这些仔细策划的数据集通常具有百万或更多的图像，跨越千分之一或更多的不同类别。创建和策划此类数据集的过程是一个巨大的承诺，要求广泛的努力和标签费用，并需要仔细导航技术和社会问题，如标签准确性，版权所有权和内容偏见。如果我们有一种方法来利用大型图像数据集的力量，但有很少或没有主要问题和目前面临的关注点？本文扩展了KataOka et的最近工作。 al。 （2020），提出基于动态生成的分形图像的改进的预训练数据集。大规模图像数据集的挑战性问题成为分形预训练的优雅点：完美的标签精度为零成本;无需存储/传输大图像档案;没有隐私/人口统计偏见/不适当内容的疑虑，因为没有人类被描绘;无限的图像供应和多样性;图像是空闲/开源。也许令人惊讶的是，避免这些困难只会在表现中征收小额罚款。利用新建的预训练任务 - 多实例预测 - 我们的实验表明，微调使用分形预先培训的网络培训的网络预先培训网络的准确性的92.7-98.1％。