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%。
translated by 谷歌翻译
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.
translated by 谷歌翻译
在目前的工作中,我们表明,公式驱动的监督学习(FDSL)的表现可以匹配甚至超过Imagenet-21K的表现,而无需在视觉预训练期间使用真实的图像,人类和自我选择变压器(VIT)。例如,在ImagEnet-21K上预先训练的VIT-BASE在ImagEnet-1K上进行微调时,在ImagEnet-1K和FDSL上进行微调时显示了81.8%的TOP-1精度,当在相同条件下进行预训练时(图像数量,数量,,图像数量,超参数和时期数)。公式产生的图像避免了隐私/版权问题,标记成本和错误以及真实图像遭受的偏见,因此具有巨大的预训练通用模型的潜力。为了了解合成图像的性能,我们测试了两个假设,即(i)对象轮廓是FDSL数据集中重要的,(ii)创建标签的参数数量增加会影响FDSL预训练的性能改善。为了检验以前的假设,我们构建了一个由简单对象轮廓组合组成的数据集。我们发现该数据集可以匹配分形的性能。对于后一种假设,我们发现增加训练任务的难度通常会导致更好的微调准确性。
translated by 谷歌翻译
我们介绍了一种基于深度学习的方法,用于将空间变化的视觉材料属性(例如纹理地图或图像样式)传播到相同或类似材料的较大样本。为培训,我们利用在多个照明和专用数据增强策略下采取的材料的图像,使转移到新颖的照明条件和仿射变形。我们的模型依赖于监督的图像到图像转换框架,并且对转移域名不可知;我们展示了语义分割,普通地图和程式化。在图像类比方法之后,该方法仅需要训练数据包含与输入引导相同的视觉结构。我们的方法采用交互式速率,使其适用于材料编辑应用。我们在受控设置中彻底评估了我们的学习方法,提供了性能的定量测量。最后,我们证明训练单个材料上的模型足以推广到相同类型的材料,而无需大量数据集。
translated by 谷歌翻译
Image classification with small datasets has been an active research area in the recent past. However, as research in this scope is still in its infancy, two key ingredients are missing for ensuring reliable and truthful progress: a systematic and extensive overview of the state of the art, and a common benchmark to allow for objective comparisons between published methods. This article addresses both issues. First, we systematically organize and connect past studies to consolidate a community that is currently fragmented and scattered. Second, we propose a common benchmark that allows for an objective comparison of approaches. It consists of five datasets spanning various domains (e.g., natural images, medical imagery, satellite data) and data types (RGB, grayscale, multispectral). We use this benchmark to re-evaluate the standard cross-entropy baseline and ten existing methods published between 2017 and 2021 at renowned venues. Surprisingly, we find that thorough hyper-parameter tuning on held-out validation data results in a highly competitive baseline and highlights a stunted growth of performance over the years. Indeed, only a single specialized method dating back to 2019 clearly wins our benchmark and outperforms the baseline classifier.
translated by 谷歌翻译
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.
translated by 谷歌翻译
Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.
translated by 谷歌翻译
培训和测试监督对象检测模型需要大量带有地面真相标签的图像。标签定义图像中的对象类及其位置,形状以及可能的其他信息,例如姿势。即使存在人力,标签过程也非常耗时。我们引入了一个新的标签工具,用于2D图像以及3D三角网格:3D标记工具(3DLT)。这是一个独立的,功能丰富和跨平台软件,不需要安装,并且可以在Windows,MacOS和基于Linux的发行版上运行。我们不再像当前工具那样在每个图像上分别标记相同的对象,而是使用深度信息从上述图像重建三角形网格,并仅在上述网格上标记一次对象。我们使用注册来简化3D标记,离群值检测来改进2D边界框的计算和表面重建,以将标记可能性扩展到大点云。我们的工具经过最先进的方法测试,并且在保持准确性和易用性的同时,它极大地超过了它们。
translated by 谷歌翻译
机器学习模型通常会遇到与训练分布不同的样本。无法识别分布(OOD)样本,因此将该样本分配给课堂标签会显着损害模​​型的可靠性。由于其对在开放世界中的安全部署模型的重要性,该问题引起了重大关注。由于对所有可能的未知分布进行建模的棘手性,检测OOD样品是具有挑战性的。迄今为止,一些研究领域解决了检测陌生样本的问题,包括异常检测,新颖性检测,一级学习,开放式识别识别和分布外检测。尽管有相似和共同的概念,但分别分布,开放式检测和异常检测已被独立研究。因此,这些研究途径尚未交叉授粉,创造了研究障碍。尽管某些调查打算概述这些方法,但它们似乎仅关注特定领域,而无需检查不同领域之间的关系。这项调查旨在在确定其共同点的同时,对各个领域的众多著名作品进行跨域和全面的审查。研究人员可以从不同领域的研究进展概述中受益,并协同发展未来的方法。此外,据我们所知,虽然进行异常检测或单级学习进行了调查,但没有关于分布外检测的全面或最新的调查,我们的调查可广泛涵盖。最后,有了统一的跨域视角,我们讨论并阐明了未来的研究线,打算将这些领域更加紧密地融为一体。
translated by 谷歌翻译
近年来,计算机视觉社区中最受欢迎的技术之一就是深度学习技术。作为一种数据驱动的技术,深层模型需要大量准确标记的培训数据,这在许多现实世界中通常是无法访问的。数据空间解决方案是数据增强(DA),可以人为地从原始样本中生成新图像。图像增强策略可能因数据集而有所不同,因为不同的数据类型可能需要不同的增强以促进模型培训。但是,DA策略的设计主要由具有领域知识的人类专家决定,这被认为是高度主观和错误的。为了减轻此类问题,一个新颖的方向是使用自动数据增强(AUTODA)技术自动从给定数据集中学习图像增强策略。 Autoda模型的目的是找到可以最大化模型性能提高的最佳DA策略。这项调查从图像分类的角度讨论了Autoda技术出现的根本原因。我们确定标准自动赛车模型的三个关键组件:搜索空间,搜索算法和评估功能。根据他们的架构,我们提供了现有图像AUTODA方法的系统分类法。本文介绍了Autoda领域的主要作品,讨论了他们的利弊,并提出了一些潜在的方向以进行未来的改进。
translated by 谷歌翻译
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。
translated by 谷歌翻译
Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes -from 1 example per class to 1 M total examples. BiT achieves 87.5% top-1 accuracy on ILSVRC-2012, 99.4% on CIFAR-10, and 76.3% on the 19 task Visual Task Adaptation Benchmark (VTAB). On small datasets, BiT attains 76.8% on ILSVRC-2012 with 10 examples per class, and 97.0% on CIFAR-10 with 10 examples per class. We conduct detailed analysis of the main components that lead to high transfer performance.
translated by 谷歌翻译
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.
translated by 谷歌翻译
Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with additional samples. (2) Classification performance decays precipitously as the number of training samples decreases when there is insufficient data. (3) Model trained on sample-balanced datasets still has different biases for different classes. In this work, we define and quantify the semantic scale of classes, which is used to measure the feature diversity of classes. It is exciting to find experimentally that there is a marginal effect of semantic scale, which perfectly describes the first two phenomena. Further, the quantitative measurement of semantic scale imbalance is proposed, which can accurately reflect model bias on multiple datasets, even on sample-balanced data, revealing a novel perspective for the study of class imbalance. Due to the prevalence of semantic scale imbalance, we propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework that overcomes the challenge of calculating semantic scales in real-time during iterations. Comprehensive experiments show that dynamic semantic-scale-balanced learning consistently enables the model to perform superiorly on large-scale long-tailed and non-long-tailed natural and medical datasets, which is a good starting point for mitigating the prevalent but unnoticed model bias.
translated by 谷歌翻译
大量数据集和高容量模型推动了计算机视觉和自然语言理解方面的许多最新进步。这项工作提出了一个平台,可以在体现的AI中实现类似的成功案例。我们提出了Procthor,这是一个程序生成体现的AI环境的框架。 Procthor使我们能够采样多种,交互式,可自定义和性能的虚拟环境的任意大型数据集,以训练和评估在导航,互动和操纵任务中的体现代理。我们通过10,000个生成的房屋和简单的神经模型的样本来证明procthor的能力和潜力。仅在Procthor上仅使用RGB图像训练的模型,没有明确的映射,并且没有人类任务监督在6个体现的AI基准中产生最先进的结果,用于导航,重排和手臂操纵,包括目前正在运行的Habitat 2022,AI2-- Thor重新安排2022,以及机器人挑战。我们还通过对procthor进行预训练,在下游基准测试上没有进行微调,通常会击败以前的最先进的系统,从而访问下游训练数据。
translated by 谷歌翻译
最近有一个浪涌的方法,旨在以无监督的方式分解和分段场景,即无监督的多对象分段。执行此类任务是计算机愿景的长期目标,提供解锁对象级推理,而无需致密的注释来列车分段模型。尽管取得了重大进展,但在视觉上简单的场景上开发和培训了当前的模型,描绘了纯背景上的单色物体。然而,自然界在视觉上复杂,与多样化的纹理和复杂的照明效果等混杂方面。在这项研究中,我们展示了一个名为Clevrtex的新基准,设计为比较,评估和分析算法的下一个挑战。 CLEVRTEX采用具有不同形状,纹理和光映射材料的合成场景,采用物理基于渲染技术创建。它包括图50k示例,描绘了在背景上布置的3-10个对象,使用60材料的目录创建,以及使用25种不同材料创建的10k图像的另一测试集。我们在CLEVRTEX上基准最近近期无监督的多对象分段模型,并找到所有最先进的方法无法在纹理环境中学习良好的陈述,尽管在更简单的数据上表现令人印象深刻。我们还创建了Clevrtex DataSet的变体,控制了场景复杂性的不同方面,并探讨了各个缺点的当前方法。数据集和代码可在https://www.robots.ox.ac.uk/~vgg/research/clevrtex中获得。
translated by 谷歌翻译
Different types of mental rotation tests have been used extensively in psychology to understand human visual reasoning and perception. Understanding what an object or visual scene would look like from another viewpoint is a challenging problem that is made even harder if it must be performed from a single image. We explore a controlled setting whereby questions are posed about the properties of a scene if that scene was observed from another viewpoint. To do this we have created a new version of the CLEVR dataset that we call CLEVR Mental Rotation Tests (CLEVR-MRT). Using CLEVR-MRT we examine standard methods, show how they fall short, then explore novel neural architectures that involve inferring volumetric representations of a scene. These volumes can be manipulated via camera-conditioned transformations to answer the question. We examine the efficacy of different model variants through rigorous ablations and demonstrate the efficacy of volumetric representations.
translated by 谷歌翻译
神经隐式表示将表面编码为应用于空间坐标的神经网络的水平集,已证明对优化,压缩和生成3D几何形状非常有效。尽管这些表示易于拟合,但尚不清楚如何最好地评估形状上的几何查询,例如与射线相交或找到最接近的点。主要的方法是鼓励网络具有签名的距离属性。但是,该属性通常仅持有大约导致鲁棒性问题,并且仅在培训结束时持有,从而抑制了在损失功能中使用查询的使用。取而代之的是,这项工作提出了一种新的方法,可以直接针对广泛的现有架构进行一般神经隐式功能进行查询。我们的关键工具是使用自动算术规则将范围分析应用于神经网络,以限制网络在区域上的输出。我们对神经网络的范围分析进行了研究,并确定了非常有效的仿射算术变体。我们使用所得边界来开发几何查询,包括射线铸造,交叉测试,构建空间层次结构,快速网格提取,最接近的点评估,评估批量特性等。我们的疑问可以在GPU上有效评估,并在随机定位的网络上提供具体的准确性,从而可以在培训目标及其他方面使用。我们还展示了对反渲染的初步应用。
translated by 谷歌翻译
深度神经网络在人类分析中已经普遍存在,增强了应用的性能,例如生物识别识别,动作识别以及人重新识别。但是,此类网络的性能通过可用的培训数据缩放。在人类分析中,对大规模数据集的需求构成了严重的挑战,因为数据收集乏味,廉价,昂贵,并且必须遵守数据保护法。当前的研究研究了\ textit {合成数据}的生成,作为在现场收集真实数据的有效且具有隐私性的替代方案。这项调查介绍了基本定义和方法,在生成和采用合成数据进行人类分析时必不可少。我们进行了一项调查,总结了当前的最新方法以及使用合成数据的主要好处。我们还提供了公开可用的合成数据集和生成模型的概述。最后,我们讨论了该领域的局限性以及开放研究问题。这项调查旨在为人类分析领域的研究人员和从业人员提供。
translated by 谷歌翻译
我们介绍了几个新的数据集即想象的A / O和Imagenet-R以及合成环境和测试套件,我们称为CAOS。 Imagenet-A / O允许研究人员专注于想象成剩余的盲点。由于追踪稳健的表示,以特殊创建了ImageNet-R,因为表示不再简单地自然,而是包括艺术和其他演绎。 Caos Suite由Carla Simulator构建,允许包含异常物体,可以创建可重复的合成环境和用于测试稳健性的场景。所有数据集都是为测试鲁棒性和衡量鲁棒性的衡量进展而创建的。数据集已用于各种其他作品中,以衡量其具有鲁棒性的自身进步,并允许切向进展,这些进展不会完全关注自然准确性。鉴于这些数据集,我们创建了几种旨在推进鲁棒性研究的新方法。我们以最大Logit的形式和典型程度的形式构建简单的基线,并以深度的形式创建新的数据增强方法,从而提高上述基准。最大Logit考虑Logit值而不是SoftMax操作后的值,而微小的变化会产生明显的改进。典型程分将输出分布与类的后部分布进行比较。我们表明,除了分段任务之外,这将提高对基线的性能。猜测可能在像素级别,像素的语义信息比类级信息的语义信息不太有意义。最后,新的Deepaulment的新增强技术利用神经网络在彻底不同于先前使用的传统几何和相机的转换的图像上创建增强。
translated by 谷歌翻译