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
translated by 谷歌翻译
本文介绍了用于学习对象级别,语言感知和富含语义的视觉表示的接地语言图像预培训(GLIP)模型。 Glip统一对象检测和短语进行预培训。统一带来了两个好处:1)它允许GLIP从检测和接地数据中学习,以改善两个任务和引导良好的接地模型; 2)GLIP可以通过以自培训方式产生接地盒来利用大规模的图像文本对,使学习的表示是语义丰富的。在我们的实验中,我们在27M的接地数据上预先列车触胶,包括3M人的注释和24M Web爬网的图像文本对。学习的表示表明了强烈的零射击和对各种对象识别任务的可转换性。 1)直接在Coco和LVIS上评估(在训练期间没有在Coco中看到任何图像)时,Plip分别达到49.8 AP和26.9 AP,超过许多监督基线。 2)在COCO上微调后,GLIP在Val和61.5 AP上实现60.8 AP在测试开发上,超过先前的SOTA。 3)当转移到下游对象检测任务时,具有完全监控动态头的1次触发器竞争对手。代码将在https://github.com/microsoft/glip发布。
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
自动视觉解对我们多样化和开放的世界需要计算机视觉模型,以概括为特定任务的最小定制,类似于人类视力。计算机视觉基础型号培训,培训多样化,大型数据集,可以适应各种下游任务,对该任务来解决现实世界计算机视觉应用而言至关重要。虽然现有的视觉基础模型如剪辑,对齐和吴道2.0主要集中在映射图像和文本表示到跨模型共享表示,我们介绍了一台新的计算机视觉基础模型,佛罗伦萨,扩大粗糙的表示(现场)到精细(对象),从静态(图像)到动态(视频),以及从RGB到多个模态(标题,深度)。通过从Web级图像文本数据中纳入通用视觉语言表示,我们的佛罗伦萨模型可以很容易地适应各种计算机视觉任务,例如分类,检索,对象检测,VQA,图像标题,视频检索和动作识别。此外,佛罗伦萨在许多类型的转移学习中表现出出色的表现:全面采样的微调,线性探测,几次射击传输和用于新颖图像和物体的零拍摄传输。所有这些属性对于我们的视觉基础模型至关重要,以提供通用视觉任务。佛罗伦萨实现了新的最先进的导致44个代表性基准,例如Imagenet-1K零射击分类,最高1精度为83.74,最高5个精度为97.18,62.4地图上的Coco微调, 80.36在VQA上,动力学-600上的87.8。
translated by 谷歌翻译
诸如剪辑之类的大型预训练的视觉模型在学习表现方面表现出巨大的潜力,这些模型可以在各种下游任务中转移。与主要基于离散标签的传统表示学习不同,视觉语言预训练会使图像和文本在公共特征空间中对齐,这允许通过提示零弹性转移到下游任务,即从分类权重合成。描述兴趣类的自然语言。在这项工作中,我们表明,在实践中部署此类模型的一个重大挑战是及时的工程,它需要域专业知识,并且非常耗时 - 由于措辞的略有变化,需要花费大量时间来进行单词调整可能会对性能产生巨大影响。受到自然语言处理(NLP)迅速学习研究的最新进展的启发,我们提出了上下文优化(COP),这是一种专门用于调整类似剪辑的视觉语言模型的简单方法,用于下游图像识别。具体而言,Coop用可学习的向量建模了提示A的上下文单词,而整个预训练的参数则保持固定。为了处理不同的图像识别任务,我们提供了两个COOP的实现:统一上下文和特定于班级的上下文。通过在11个数据集上进行的大量实验,我们证明Coop只需要一两个镜头才能以相当的利润击败手工制作的提示,并且能够以16张镜头(例如16张照片)获得迅速工程的显着改进增益约为15%(最高达到45%以上)。尽管是一种基于学习的方法,但与使用手工制作的提示相比,Coop与零拍模型相比,取得了出色的域泛化性能。
translated by 谷歌翻译
预训练的视觉模型(例如,剪辑)在许多下游任务中显示出有希望的零弹性概括,并具有正确设计的文本提示。最近的作品不依赖手工设计的提示,而是使用下游任务的培训数据来学习提示。虽然有效,但针对领域数据的培训却降低了模型的概括能力,使其无法看到新领域。在这项工作中,我们提出了测试时间提示调整(TPT),该方法可以通过单个测试样本即时学习自适应提示。对于图像分类,TPT通过使用置信度选择最小化熵来优化提示,以便模型在每个测试样本的不同增强视图上都具有一致的预测。在评估对自然分布变化的概括时,TPT平均将零击的TOP-1精度提高了3.6%,超过了先前需要其他特定于任务的训练数据的迅速调整方法。在评估看不见类别的跨数据集泛化时,TPT与使用其他培训数据的最先进方法相当。项目页面:https://azshue.github.io/tpt。
translated by 谷歌翻译
本文提出了一种对比调整,这是一种简单的方法,采用对比训练来对准图像和文本模型,同时仍然利用他们的预训练。在我们的实证研究中,我们发现,锁定的预训练图像模型与解锁文本模型最佳。我们调用这种对比调整“锁定图像文本调整”(LIT TOONING)的实例,该实例仅教导文本模型,从预先训练的图像模型中读出了良好的表示新任务。亮度调谐模型将零拍摄传输到新视觉任务的能力提高,例如图像分类或检索。建议的亮度调整是广泛适用的;它可以使用三种不同的图像文本数据集可靠地使用多种预训练方法(监督和无监督)和多种架构(Reset,Vision变换器和MLP-MILLER)。利用基于变压器的预训练VIT-G / 14型号,LIT调谐模型在想象网测试集中实现了84.5%的零射频传输精度,并且在充满挑战的分发ObjectNet测试集中实现了81.1%。
translated by 谷歌翻译
视觉语言预训练(VLP)模型在各种下游任务上表现出色。他们的成功在很大程度上取决于预训练的跨模式数据集的规模。但是,中文中缺乏大规模数据集和基准阻碍了中国VLP模型和更广泛的多语言应用程序的发展。在这项工作中,我们发布了一个名为Wukong的大型中国跨模式数据集,其中包含从网络收集的1亿个中文图像文本对。 Wukong旨在基准基准不同的多模式预训练方法,以促进VLP研究和社区发展。此外,我们发布了一组模型,预先训练了各种图像编码器(vit-b/vit-l/swint),还将高级预训练技术应用于VLP,例如锁定图像文本调整,相对于代币的相似性学习和减少互动。还提供了广泛的实验和不同下游任务的基准测试,包括新的最大人验证的图像文本测试数据集。实验表明,Wukong可以作为不同的跨模式学习方法的有前途的中国预培训数据集和基准。对于10个数据集上的零摄像图像分类任务,$ Wukong_ {vit-l} $达到的平均准确度为73.03%。对于图像文本检索任务,它在AIC-ICC上的平均召回率为71.6%,比Wenlan 2.0高12.9%。此外,我们的Wukong模型在下游任务上进行了基准测试,例如多个数据集上的其他变体,例如Flickr8k-CN,Flickr-30K-CN,Coco-CN,Coco-CN等。更多信息可以参考:https://wukong-dataset.github.io/wukong-dataset/。
translated by 谷歌翻译
Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing approaches usually consider learning prompt vectors for each task independently from scratch, thereby failing to exploit the rich shareable knowledge across different vision-language tasks. In this paper, we propose multitask vision-language prompt tuning (MVLPT), which incorporates cross-task knowledge into prompt tuning for vision-language models. Specifically, (i) we demonstrate the effectiveness of learning a single transferable prompt from multiple source tasks to initialize the prompt for each target task; (ii) we show many target tasks can benefit each other from sharing prompt vectors and thus can be jointly learned via multitask prompt tuning. We benchmark the proposed MVLPT using three representative prompt tuning methods, namely text prompt tuning, visual prompt tuning, and the unified vision-language prompt tuning. Results in 20 vision tasks demonstrate that the proposed approach outperforms all single-task baseline prompt tuning methods, setting the new state-of-the-art on the few-shot ELEVATER benchmarks and cross-task generalization benchmarks. To understand where the cross-task knowledge is most effective, we also conduct a large-scale study on task transferability with 20 vision tasks in 400 combinations for each prompt tuning method. It shows that the most performant MVLPT for each prompt tuning method prefers different task combinations and many tasks can benefit each other, depending on their visual similarity and label similarity. Code is available at https://github.com/sIncerass/MVLPT.
translated by 谷歌翻译
Contrastive Language-Image Pre-trained (CLIP) models have zero-shot ability of classifying an image belonging to "[CLASS]" by using similarity between the image and the prompt sentence "a [CONTEXT] of [CLASS]". Based on exhaustive text cues in "[CONTEXT]", CLIP model is aware of different contexts, e.g. background, style, viewpoint, and exhibits unprecedented robustness against a wide range of distribution shifts. However, recent works find further fine-tuning of CLIP models improves accuracy but sacrifices the robustness on downstream tasks. We conduct an empirical investigation to show fine-tuning will corrupt the context-aware ability of pre-trained CLIP features. To solve this problem, we propose Context-Aware Robust Fine-tuning (CAR-FT). CAR-FT regularizes the model during fine-tuning to capture the context information. Specifically, we use zero-shot prompt weights to get the context distribution contained in the image. By minimizing the Kullback-Leibler Divergence (KLD) between context distributions induced by original/fine-tuned CLIP models, CAR-FT makes the context-aware ability of CLIP inherited into downstream tasks, and achieves both higher In-Distribution (ID) and Out-Of-Distribution (OOD) accuracy. The experimental results show CAR-FT achieves superior robustness on five OOD test datasets of ImageNet, and meanwhile brings accuracy gains on nine downstream tasks. Additionally, CAR-FT surpasses previous Domain Generalization (DG) methods and gets 78.5% averaged accuracy on DomainBed benchmark, building the new state-of-the-art.
translated by 谷歌翻译
Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks including zero-shot classification, retrieval, linear probing, and end-to-end fine-tuning. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures and similar training recipes. We open-source our evaluation workflow and all models, including the largest public CLIP models, to ensure reproducibility and make scaling laws research more accessible. Source code and instructions to reproduce this study will be available at https://github.com/LAION-AI/scaling-laws-openclip
translated by 谷歌翻译
视觉语言预培训对从大规模Web数据学习联合视觉文本表示的巨大成功,展示了零拍广泛的显着能力。本文介绍了一种简单的方法,可以将一个预先训练的视觉语言模型有效地调整到具有最小培训的新型任务,以及这里,我们考虑视频了解任务。具体而言,我们建议优化几个随机向量,称为连续提示向量,将新颖任务转换为与预培训目标相同的格式。此外,为了弥合静态图像和视频之间的差距,用堆叠在框架明智的视觉特征之上的轻量压变压器编码时分信息。在实验上,我们进行广泛的消融研究,以分析关键组成部分和必需品。在9个公共基准的行动认可,行动本地化和文本 - 视频检索,跨封闭式,几次射击,开放式场景,我们为现有方法实现了竞争或最先进的性能,尽管培训显着更少的参数。
translated by 谷歌翻译
The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pretraining. However, these datasets are often collected with overrestrictive requirements inherited from their original target tasks (e.g., image caption generation), which limit the resulting dataset scale and diversity. We take a step further in pushing the limits of vision-and-language pretraining data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [70] and introduce the Conceptual 12M (CC12M), a dataset with 12 million image-text pairs specifically meant to be used for visionand-language pre-training. We perform an analysis of this dataset and benchmark its effectiveness against CC3M on multiple downstream tasks with an emphasis on long-tail visual recognition. Our results clearly illustrate the benefit of scaling up pre-training data for vision-and-language tasks, as indicated by the new state-of-the-art results on both the nocaps and Conceptual Captions benchmarks. 1
translated by 谷歌翻译
从任务不足的预训练的深层模型中转移知识以进行下游任务是计算机视觉研究中的一个重要主题。随着计算能力的增长,我们现在拥有大规模的模型体系结构和数据量的开源视觉语言预培训模型。在这项研究中,我们专注于转移视力分类任务的知识。传统方法随机初始化线性分类器头进行视觉分类,但是它们将文本编码器的用法留为未发现的下游视觉识别任务。在本文中,我们修改了线性分类器的角色,并用对象类别的嵌入式语言表示替换分类器。这些语言表示是从视觉语言预训练模型的文本编码器初始化的,以进一步利用其良好的语言模型参数。实证研究表明,我们的方法提高了视频分类的性能和训练速度,模型的变化微不足道。特别是,我们的范式在动力学400上实现了87.3%的最新准确性。
translated by 谷歌翻译
当前的Modus Operandi在改编预训练的模型中涉及更新所有骨干参数,即,完整的微调。本文介绍了视觉及时调整(VPT),作为视觉中大规模变压器模型的全面微调的有效替代方案。VPT从最近有效地调整大型语言模型的最新进展中汲取灵感,在输入空间中仅引入了少量的可训练参数(少于模型参数),同时保持模型骨架冻结。通过对各种下游识别任务的广泛实验,我们表明VPT与其他参数有效调整协议相比获得了显着的性能增长。最重要的是,在许多情况下,VPT甚至在模型能力和培训数据量表的许多情况下都胜过全面的微调,同时降低了每任务的存储成本。
translated by 谷歌翻译
本文研究了两种技术,用于开发有效的自我监督视觉变压器(ESVIT)进行视觉表示学习。首先,我们通过一项全面的实证研究表明,具有稀疏自我生产的多阶段体系结构可以显着降低建模的复杂性,但具有失去捕获图像区域之间细粒度对应关系的能力的成本。其次,我们提出了一项新的区域匹配训练任务,该任务使模型可以捕获细粒的区域依赖性,因此显着提高了学习视觉表示的质量。我们的结果表明,ESVIT在ImageNet线性探针评估上结合两种技术,在ImageNet线性探针评估中获得了81.3%的TOP-1,优于先前的艺术,其较高吞吐量的顺序幅度约为较高。当转移到下游线性分类任务时,ESVIT在18个数据集中的17个中优于其受监督的对方。代码和模型可公开可用:https://github.com/microsoft/esvit
translated by 谷歌翻译
Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in the finetuning process can lead to surprisingly large differences in the final performance, both for in-distribution (ID) and out-of-distribution (OOD) data. In this work, we show that a natural and simple approach of mimicking contrastive pretraining consistently outperforms alternative finetuning approaches. Specifically, we cast downstream class labels as text prompts and continue optimizing the contrastive loss between image embeddings and class-descriptive prompt embeddings (contrastive finetuning). Our method consistently outperforms baselines across 7 distribution shifts, 6 transfer learning, and 3 few-shot learning benchmarks. On WILDS-iWILDCam, our proposed approach FLYP outperforms the top of the leaderboard by $2.3\%$ ID and $2.7\%$ OOD, giving the highest reported accuracy. Averaged across 7 OOD datasets (2 WILDS and 5 ImageNet associated shifts), FLYP gives gains of $4.2\%$ OOD over standard finetuning and outperforms the current state of the art (LP-FT) by more than $1\%$ both ID and OOD. Similarly, on 3 few-shot learning benchmarks, our approach gives gains up to $4.6\%$ over standard finetuning and $4.4\%$ over the state of the art. In total, these benchmarks establish contrastive finetuning as a simple, intuitive, and state-of-the-art approach for supervised finetuning of image-text models like CLIP. Code is available at https://github.com/locuslab/FLYP.
translated by 谷歌翻译
视觉模型最近在许多计算机视觉任务上显示出巨大的潜力。同时,与线性探针相比,先前的工作表明,与线性探针相比,这是较少的图像识别的迅速调整,可以在很少的图像识别上获得卓越的性能。在实际应用程序中,相关的几个射击任务是相关的,尤其是在专业领域。但是,以前的工作忽略了此类信息。受到以下事实的启发,即通过多任务学习通常可以提高性能,我们提出了一种新颖的方法softcpt(迅速调整的软上下文共享),以微调多个目标几个目标任务的预训练的视觉模型, 同时。具体来说,我们设计了一个任务共享的元网络,以使用预定义的任务名称以及可学习的元提示为输入为每个任务生成提示向量。因此,所有任务的迅速向量将以软的方式共享。该共享的元网络的参数以及元提示向量都在所有目标任务的联合培训集中调整。在三个多任务少量数据集上进行的广泛实验表明,SoftCpt的表现优于代表性的单任务提示方法Coop [78],这意味着多任务学习在视觉及时及时调整中的有效性。源代码和数据将公开可用。
translated by 谷歌翻译
We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple first-person and third-person video tasks, both in zero-shot and finetuned setups. Most notably, LaViLa obtains an absolute gain of 10.1% on EGTEA classification and 5.9% Epic-Kitchens-100 multi-instance retrieval benchmarks. Furthermore, LaViLa trained with only half the narrations from the Ego4D dataset outperforms baseline models trained on the full set, and shows positive scaling behavior on increasing pre-training data and model size.
translated by 谷歌翻译
将简单的体系结构与大规模预训练相结合已导致图像分类的大量改进。对于对象检测,预训练和缩放方法的确定性不佳,尤其是在长尾和开放式摄影的环境中,训练数据相对较少。在本文中,我们提出了一个强大的配方,用于将图像文本模型转移到开放式对象检测中。我们使用具有最小修改,对比度文本预训练和端到端检测微调的标准视觉变压器体系结构。我们对该设置的缩放属性的分析表明,增加图像级预训练和模型大小在下游检测任务上产生一致的改进。我们提供适应性策略和正规化,以实现零击文本条件和单次图像条件对象检测的非常强劲的性能。代码和型号可在GitHub上找到。
translated by 谷歌翻译