在过去的十年中,基于学习的图像质量评估(IQA)取得了显着的进步,但几乎所有人都考虑了两个关键组成部分 - 模型和数据 - 相对隔离。具体而言,以模型为中心的IQA着重于在固定和广泛重复使用的数据集上开发“更好”的客观质量方法,并具有过度拟合的危险。以数据为中心的IQA涉及进行心理物理实验来构建“更好”的人类通知数据集,不幸的是,在数据集创建期间,它忽略了当前的IQA模型。在本文中,我们首先设计了一系列实验,以计算探测模型和数据的这种隔离会阻碍IQA的进一步进展。然后,我们描述一个集成了以模型为中心和数据的IQA的计算框架。作为一个具体示例,我们设计了计算模块,以量化基于盲人IQA(BIQA)模型预测和深度内容感知特征的候选图像的值得采样性。实验结果表明,所提出的值得采样的模块成功地发现了所检查的BIQA模型的各种故障,这些模型确实值得包括在下一代数据集中。
translated by 谷歌翻译
在过去的几十年中,盲目的图像质量评估(BIQA)旨在准确地预测图像质量而无需任何原始参考信息,但一直在广泛关注。特别是,在深层神经网络的帮助下,取得了巨大进展。但是,对于夜间图像(NTI)的BIQA的研究仍然较少,通常患有复杂的真实扭曲,例如可见性降低,低对比度,添加噪声和颜色失真。这些多样化的真实降解特别挑战了有效的深神网络的设计,用于盲目NTI质量评估(NTIQE)。在本文中,我们提出了一个新颖的深层分解和双线性池网络(DDB-NET),以更好地解决此问题。 DDB-NET包含三个模块,即图像分解模块,一个特征编码模块和双线性池模块。图像分解模块的灵感来自Itinex理论,并涉及将输入NTI解耦到负责照明信息的照明层组件和负责内容信息的反射层组件。然后,编码模块的功能涉及分别植根于两个解耦组件的降解的特征表示。最后,通过将照明相关和与内容相关的降解作为两因素变化进行建模,将两个特征集组合在一起,将双线汇总在一起以形成统一的表示,以进行质量预测。在几个基准数据集上进行了广泛的实验,已对所提出的DDB-NET的优势得到了很好的验证。源代码将很快提供。
translated by 谷歌翻译
As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given the dominance of deep neural network based models, which are composed of a large number of parameters and data hungry, in application. Despite its indispensable role for developing AI models, research on active learning is not as intensive as other research directions. In this paper, we present a review of active learning through deep active learning approaches from the following perspectives: 1) technical advancements in active learning, 2) applications of active learning in computer vision, 3) industrial systems leveraging or with potential to leverage active learning for data iteration, 4) current limitations and future research directions. We expect this paper to clarify the significance of active learning in a modern AI model manufacturing process and to bring additional research attention to active learning. By addressing data automation challenges and coping with automated machine learning systems, active learning will facilitate democratization of AI technologies by boosting model production at scale.
translated by 谷歌翻译
随着高动态范围(HDR)摄影的日益普及和可访问性,用于动态范围压缩和中等呈现的音调映射操作员(TMO)实际上是要求的。在本文中,我们开发了一种基于生物学的,计算效率和感知优化的两阶段神经网络图像TMO。在第一阶段,由人类视觉系统(HVS)早期阶段的生理学动机,我们首先将HDR图像分解为标准化的Laplacian金字塔。然后,我们使用两个轻巧的深神经网络(DNN),将这种归一化表示作为输入并估计相应LDR图像的拉普拉斯金字塔。我们通过最小化标准化的拉普拉斯金字塔距离(NLPD)来优化音调映射网络,这是一种对人类对音调映射图像质量判断的校准的感知度量。在第二阶段中,我们通过输入HDR图像``校准'',生成具有不同颜色饱和度和细节可见性的伪型曝光图像堆栈。然后,我们通过最大化MEF-SSIM的变体,这是另一个具有感知校准的度量以进行图像融合,将另一个轻巧的DNN训练将LDR图像堆叠融合到所需的LDR图像中。通过这样做,提出的TMO是完全自动的,以映射未校准的HDR图像。在一组独立的HDR图像中,我们发现我们的方法生成具有更好的视觉质量的图像,并且是本地最快的TMO之一。
translated by 谷歌翻译
无参考图像质量评估(NR-IQA)的目标是根据主观评估来估计感知图像质量,由于不存在原始参考图像,它是复杂和未解决的问题。在本文中,我们提出了一种新颖的模型来解决NR-IQA任务,利用卷积神经网络(CNNS)和变压器中的自我关注机制来解决来自输入图像的本地和非局部特征的混合方法来解决NR-IQA任务。我们通过CNN捕获图像的局部结构信息,然后避免提取的CNNS特征之间的局部偏压并获得图像的非本地表示,我们利用所提取的特征上的变压器,其中我们将它们塑造为顺序输入变压器模型。此外,为了改善主观和目标分数之间的单调性相关性,我们利用每个批处理内图像之间的相对距离信息,并强制执行它们之间的相对排名。最后但并非最不重要的是,我们观察到NR-IQA模型的性能在我们应用于输入到输入时申请等级变换(例如水平翻转)。因此,我们提出了一种利用自我保持性作为自我监督来源的方法,以改善NRIQA模型的鲁棒性。具体而言,我们为每个图像的质量评估模型的输出和其转换(水平翻转)强制实施自我一致性,以利用丰富的自我监控信息,并降低模型的不确定性。为了展示我们工作的有效性,我们在七个标准IQA数据集(合成和真实)上评估它,并显示我们的模型在各种数据集上实现最先进的结果。
translated by 谷歌翻译
Scale-invariance is an open problem in many computer vision subfields. For example, object labels should remain constant across scales, yet model predictions diverge in many cases. This problem gets harder for tasks where the ground-truth labels change with the presentation scale. In image quality assessment (IQA), downsampling attenuates impairments, e.g., blurs or compression artifacts, which can positively affect the impression evoked in subjective studies. To accurately predict perceptual image quality, cross-resolution IQA methods must therefore account for resolution-dependent errors induced by model inadequacies as well as for the perceptual label shifts in the ground truth. We present the first study of its kind that disentangles and examines the two issues separately via KonX, a novel, carefully crafted cross-resolution IQA database. This paper contributes the following: 1. Through KonX, we provide empirical evidence of label shifts caused by changes in the presentation resolution. 2. We show that objective IQA methods have a scale bias, which reduces their predictive performance. 3. We propose a multi-scale and multi-column DNN architecture that improves performance over previous state-of-the-art IQA models for this task, including recent transformers. We thus both raise and address a novel research problem in image quality assessment.
translated by 谷歌翻译
用户生成的内容(UGC)的盲或禁区视频质量评估已成为趋势,具有挑战性,迄今未解决的问题。因此,适用于该内容的准确和高效的视频质量预测因素都需要实现更智能的分析和处理UGC视频的需求。以前的研究表明,自然场景统计和深度学习特征既足以捕获空​​间扭曲,这有助于UGC视频质量问题的重要方面。然而,这些模型无法对实际应用中预测复杂和不同的UGC视频的质量无能为力或效率低。在这里,我们为UGC含量介绍了一种有效且高效的视频质量模型,我们将我们展示快速准确的视频质量评估员(Rapique),我们展示了与最先进的(SOTA)模型相对表现,而是具有订单-magnitude更快的运行时。 Rapique结合并利用了质量意识的现场统计特征和语义知识的深度卷积功能的优势,使我们能够设计用于视频质量建模的第一通用和有效的空间和时间(时空)带通统计模型。我们对最近的大型UGC视频质量数据库的实验结果表明,Rapique以相当更低的计算费用提供所有数据集的顶级表现。我们希望这项工作促进并激发进一步努力实现潜在的实时和低延迟应用程序的视频质量问题的实际建模。为促进公共用途,在线进行了求助的实施:\ url {https://github.com/vztu/rapique}。
translated by 谷歌翻译
Objective methods for assessing perceptual image quality have traditionally attempted to quantify the visibility of errors between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a Structural Similarity Index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000. 1
translated by 谷歌翻译
在本文中,我们提出了通过特征级伪参考(PR)幻觉提出的无引用(NR)图像质量评估(IQA)方法。提出的质量评估框架基于自然图像统计行为的先前模型,并植根于以下观点,即可以很好地利用具有感知意义的特征来表征视觉质量。本文中,通过以原始参考为监督的相互学习方案学习了扭曲的图像中的PR特征,并通过三重态约束进一步确保PR特征的区分特性。给定质量推断的扭曲图像,特征水平的分离是用可逆神经层进行最终质量预测的,导致PR和相应的失真特征以进行比较。在四个流行的IQA数据库中证明了我们提出的方法的有效性,跨数据库评估的卓越性能也揭示了我们方法的高概括能力。我们的方法的实现可在https://github.com/baoliang93/fpr上公开获得。
translated by 谷歌翻译
主动学习(al)试图通过标记最少的样本来最大限度地提高模型的性能增益。深度学习(DL)是贪婪的数据,需要大量的数据电源来优化大量参数,因此模型了解如何提取高质量功能。近年来,由于互联网技术的快速发展,我们处于信息种类的时代,我们有大量的数据。通过这种方式,DL引起了研究人员的强烈兴趣,并已迅速发展。与DL相比,研究人员对Al的兴趣相对较低。这主要是因为在DL的崛起之前,传统的机器学习需要相对较少的标记样品。因此,早期的Al很难反映其应得的价值。虽然DL在各个领域取得了突破,但大多数这一成功都是由于大量现有注释数据集的宣传。然而,收购大量高质量的注释数据集消耗了很多人力,这在某些领域不允许在需要高专业知识,特别是在语音识别,信息提取,医学图像等领域中, al逐渐受到适当的关注。自然理念是AL是否可用于降低样本注释的成本,同时保留DL的强大学习能力。因此,已经出现了深度主动学习(DAL)。虽然相关的研究非常丰富,但它缺乏对DAL的综合调查。本文要填补这一差距,我们为现有工作提供了正式的分类方法,以及全面和系统的概述。此外,我们还通过申请的角度分析并总结了DAL的发展。最后,我们讨论了DAL中的混乱和问题,为DAL提供了一些可能的发展方向。
translated by 谷歌翻译
Recent years witnessed the breakthrough of face recognition with deep convolutional neural networks. Dozens of papers in the field of FR are published every year. Some of them were applied in the industrial community and played an important role in human life such as device unlock, mobile payment, and so on. This paper provides an introduction to face recognition, including its history, pipeline, algorithms based on conventional manually designed features or deep learning, mainstream training, evaluation datasets, and related applications. We have analyzed and compared state-of-the-art works as many as possible, and also carefully designed a set of experiments to find the effect of backbone size and data distribution. This survey is a material of the tutorial named The Practical Face Recognition Technology in the Industrial World in the FG2023.
translated by 谷歌翻译
感知视频质量评估(VQA)是许多流和视频共享平台的组成部分。在这里,我们以自我监督的方式考虑学习具有感知相关的视频质量表示的问题。失真类型的识别和降解水平确定被用作辅助任务,以训练一个深度学习模型,该模型包含深度卷积神经网络(CNN),该模型提取了空间特征,以及捕获时间信息的复发单元。该模型是使用对比度损失训练的,因此我们将此训练框架和结果模型称为对比度质量估计器(Conviqt)。在测试过程中,训练有素的模型的权重被冷冻,并且线性回归器将学习的功能映射到No-Reference(NR)设置中的质量得分。我们通过分析模型预测与地面真相质量评级之间的相关性,并与最先进的NR-VQA模型相比,我们对多个VQA数据库进行了全面评估,并实现竞争性能在这些数据库上进行了培训。我们的消融实验表明,学到的表示形式非常强大,并且在合成和现实的扭曲中很好地概括了。我们的结果表明,可以使用自我监督的学习来获得具有感知轴承的引人注目的表示。这项工作中使用的实现已在https://github.com/pavancm/conviqt上提供。
translated by 谷歌翻译
One of the main challenges in deep learning-based underwater image enhancement is the limited availability of high-quality training data. Underwater images are difficult to capture and are often of poor quality due to the distortion and loss of colour and contrast in water. This makes it difficult to train supervised deep learning models on large and diverse datasets, which can limit the model's performance. In this paper, we explore an alternative approach to supervised underwater image enhancement. Specifically, we propose a novel unsupervised underwater image enhancement framework that employs a conditional variational autoencoder (cVAE) to train a deep learning model with probabilistic adaptive instance normalization (PAdaIN) and statistically guided multi-colour space stretch that produces realistic underwater images. The resulting framework is composed of a U-Net as a feature extractor and a PAdaIN to encode the uncertainty, which we call UDnet. To improve the visual quality of the images generated by UDnet, we use a statistically guided multi-colour space stretch module that ensures visual consistency with the input image and provides an alternative to training using a ground truth image. The proposed model does not need manual human annotation and can learn with a limited amount of data and achieves state-of-the-art results on underwater images. We evaluated our proposed framework on eight publicly-available datasets. The results show that our proposed framework yields competitive performance compared to other state-of-the-art approaches in quantitative as well as qualitative metrics. Code available at https://github.com/alzayats/UDnet .
translated by 谷歌翻译
视频质量评估(VQA)仍然是一个重要而挑战性的问题,影响了最广泛的尺度的许多应用程序。移动设备和云计算技术的最新进展使得可以捕获,处理和共度高分辨率,高分辨率(HFR)视频几乎瞬间。能够监控和控制这些流式视频的质量可以使得能够提供更令人愉快的内容和感知的优化速率控制。因此,需要一种强迫需要开发可以在巨大尺度部署的VQA模型。虽然最近的一些效果已应用于可变帧速率和HFR视频质量的全参考(FR)分析,但是没有研究帧速率变化的无引用(NR)VQA算法的开发。在这里,我们提出了一种用于评估HFR视频的一级盲VQA模型,我们将其配给了帧群感知视频评估程序W / O参考(Faver)。 Faver使用扩展模型的空间自然场景统计数据,即包括节省空间小波分解的视频信号,进行有效的帧速率敏感质量预测。我们对几个HFR视频质量数据集的广泛实验表明,PEVER以合理的计算成本优于其他盲VQA算法。为了便于可重复的研究和公共评估,在线可以在线进行狂热的实施:\ url {https://github.com/uniqzheng/hfr-bvqa}。
translated by 谷歌翻译
自然图像的统计规律(称为自然场景统计数据)在不引用图像质量评估中起重要作用。但是,人们普遍认为,通常是计算机生成的屏幕内容图像(SCI)不持有此类统计信息。在这里,我们首次尝试学习SCI的统计数据,基于可以有效确定SCI的质量。所提出的方法的基本机制是基于一个狂野的假设,即没有物理上获得的SCI仍然遵守某些可以以学习方式理解的统计数据。我们从经验上表明,在质量评估中可以有效利用统计偏差,并且在不同的环境中进行评估时,提出的方法优越。广泛的实验结果表明,与现有的NR-IQA模型相比,基于深度统计的SCI质量评估(DFSS-IQA)模型可提供有希望的性能,并在跨数据库设置中显示出很高的概括能力。我们的方法的实现可在https://github.com/baoliang93/dfss-iqa上公开获得。
translated by 谷歌翻译
用户生成的内容(UGC)的盲图质量评估(BIQA)遭受范围效应,表明在整体质量范围,平均意见评分(MOS)和预测的MOS(PMO)(PMO)上有很好的相关性;关注特定范围,相关性较低。范围效应的原因是,在较大范围内和狭窄范围内的预测偏差破坏了MOS和PMO之间的均匀性。为了解决这个问题,提出了一种新的方法,从粗粒度度量到细粒度的预测。首先,我们为粗粒度度量设计了排名和梯度损失。损失保持了PMOS和MOS之间的顺序和毕业生一致性,从而在较大范围内减少了预测的偏差。其次,我们提出多级公差损失以进行细粒度的预测。损失受到减少阈值的限制,以限制较窄和较窄范围的预测偏差。最后,我们设计了一个反馈网络来进行粗到精细的评估。一方面,网络采用反馈块来处理多尺度的失真功能,另一方面,它将非本地上下文功能融合到每次迭代的输出中,以获取更多质量感知的功能表示。实验结果表明,与最先进的方法相比,提出的方法可以减轻范围效应。
translated by 谷歌翻译
在极低光线条件下捕获图像会对标准相机管道带来重大挑战。图像变得太黑了,太吵了,这使得传统的增强技术几乎不可能申请。最近,基于学习的方法已经为此任务显示了非常有希望的结果,因为它们具有更大的表现力能力来允许提高质量。这些研究中的激励,在本文中,我们的目标是利用爆破摄影来提高性能,并从极端暗的原始图像获得更加锐利和更准确的RGB图像。我们提出的框架的骨干是一种新颖的粗良好网络架构,逐步产生高质量的输出。粗略网络预测了低分辨率,去噪的原始图像,然后将其馈送到精细网络以恢复微尺的细节和逼真的纹理。为了进一步降低噪声水平并提高颜色精度,我们将该网络扩展到置换不变结构,使得它作为输入突发为低光图像,并在特征级别地合并来自多个图像的信息。我们的实验表明,我们的方法通过生产更详细和相当更高的质量的图像来引起比最先进的方法更令人愉悦的结果。
translated by 谷歌翻译
Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID has recently shifted to the open-world setting, facing more challenging issues. This setting is closer to practical applications under specific scenarios. We summarize the open-world Re-ID in terms of five different aspects. By analyzing the advantages of existing methods, we design a powerful AGW baseline, achieving state-of-the-art or at least comparable performance on twelve datasets for FOUR different Re-ID tasks. Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re-ID system for real applications. Finally, some important yet under-investigated open issues are discussed.
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
图像质量评估的计算机视觉模型(IQA)预测了通用图像降解的主观效果,例如人工制品,模糊,不良的曝光或颜色。现有IQA数据集中面部图像的稀缺性(低于10 \%)限制了准确过滤低质量的面部图像或指导面部图像处理的CV模型所需的IQA的精度,例如超分辨率,图像增强和生成。在本文中,我们首先介绍了迄今为止最大的注释IQA数据库,其中包含20,000个人体面孔(比所有现有的面孔的额定数据集大),在高度多样化的情况,质量水平和失真水平和变形类型中。基于数据库,我们进一步提出了一种新颖的深度学习模型,该模型重新塑造了生成的先验特征,以预测主观的面部质量。通过利用训练有素的生成模型中编码的丰富统计数据,我们获得了图像的生成性先验信息,并将其作为潜在参考,以促进盲目的IQA任务。实验结果证明了拟议模型在面部IQA任务上的出色预测准确性。
translated by 谷歌翻译