部件检测和语义网络的细粒度鞋类图像检索

目的 细粒度图像检索是当前细粒度图像分析和视觉领域的热点问题。以鞋类图像为例,传统方法仅提取其粗粒度特征且缺少关键的语义属性,难以区分部件间的细微差异,不能有效用于细粒度检索。针对鞋类图像检索大多基于简单款式导致检索效率不高的问题,提出一种结合部件检测和语义网络的细粒度鞋类图像检索方法。方法 结合标注后的鞋类图像训练集对输入的待检鞋类图像进行部件检测;基于部件检测后的鞋类图像和定义的语义属性训练语义网络,以提取待检图像和训练图像的特征向量,并采用主成分分析进行降维;通过对鞋类图像训练集中每个候选图像与待检图像间的特征向量进行度量学习,按其匹配度高低顺序输出检索结果。结果 实验在UT-Zap50K数据集上与目前检索效果较好的4种方法进行比较,检索精度提高近6%。同时,与同任务的SHOE-CNN（semantic hierarchy of attribute convolutional neural network）检索方法比较,本文具有更高的检索准确率。结论 针对传统图像特征缺少细微的视觉描述导致鞋类图像检索准确率低的问题,提出一种细粒度鞋类图像检索方法,既提高了鞋类图像检索的精度和准确率,又能较好地满足实际应用需求。     

结合深度多标签解析的哈希服装检索

目的 服装检索对于在线服装的推广和销售有着重要的作用。而目前的服装检索算法无法准确地检索出非文本描述的服装。特别是对于跨场景的多标签服装图片,服装检索算法的准确率还有待提升。本文针对跨场景多标签服装图片的差异性较大以及卷积神经网络输出特征维度过高的问题,提出了深度多标签解析和哈希的服装检索算法。方法 该方法首先在FCN（fully convolutional network）的基础上加入条件随机场,对FCN的结果进行后处理,搭建了FCN粗分割加CRFs（conditional random fields）精分割的端到端的网络结构,实现了像素级别的语义识别。其次,针对跨场景服装检索的特点,我们调整了CCP（Clothing Co-Parsing）数据集,并构建了Consumer-to-Shop数据集。针对检索过程中容易出现的语义漂移现象,使用多任务学习网络分别训练了衣物分类模型和衣物相似度模型。结果 我们首先在Consumer-to-Shop数据集上进行了服装解析的对比实验,实验结果表明在添加了CRFs作为后处理之后,服装解析的效果有了明显提升。然后与3种主流检索算法进行了对比,结果显示,本文方法在使用哈希特征的条件下,也可以取得较好的检索效果。在top-5正确率上比WTBI（where to buy it）高出1.31%,比DARN（dual attribute-aware ranking network）高出0.21%。结论 针对服装检索的跨场景效果差、检索效率低的问题,本文提出了一种基于像素级别语义分割和哈希编码的快速多目标服装检索方法。与其他检索方法相比,本文在多目标、多标签服装检索场景有一定的优势,并且在保持了一定检索效果的前提下,有效地降低了存储空间,提高了检索效率。     

Sparse semantic metric learning for image retrieval

Typical content-based image retrieval solutions usually cannot achieve satisfactory performance due to the semantic gap challenge. With the popularity of social media applications, large amounts of social images associated with user tagging information are available, which can be leveraged to boost image retrieval. In this paper, we propose a sparse semantic metric learning (SSML) algorithm by discovering knowledge from these social media resources, and apply the learned metric to search relevant images for users. Different from the traditional metric learning approaches that use similar or dissimilar constraints over a homogeneous visual space, the proposed method exploits heterogeneous information from two views of images and formulates the learning problem with the following principles. The semantic structure in the text space is expected to be preserved for the transformed space. To prevent overfitting the noisy, incomplete, or subjective tagging information of images, we expect that the mapping space by the learned metric does not deviate from the original visual space. In addition, the metric is straightforward constrained to be row-wise sparse with the ?_2,1-norm to suppress certain noisy or redundant visual feature dimensions. We present an iterative algorithm with proved convergence to solve the optimization problem. With the learned metric for image retrieval, we conduct extensive experiments on a real-world dataset and validate the effectiveness of our approach compared with other related work.     

Collaborative image retrieval via regularized metric learning

In content-based image retrieval (CBIR), relevant images are identified based on their similarities to query images. Most CBIR algorithms are hindered by the semantic gap between the low-level image features used for computing image similarity and the high-level semantic concepts conveyed in images. One way to reduce the semantic gap is to utilize the log data of users' feedback that has been collected by CBIR systems in history, which is also called “collaborative image retrieval.” In this paper, we present a novel metric learning approach, named “regularized metric learning,” for collaborative image retrieval, which learns a distance metric by exploring the correlation between low-level image features and the log data of users' relevance judgments. Compared to the previous research, a regularization mechanism is used in our algorithm to effectively prevent overfitting. Meanwhile, we formulate the proposed learning algorithm into a semidefinite programming problem, which can be solved very efficiently by existing software packages and is scalable to the size of log data. An extensive set of experiments has been conducted to show that the new algorithm can substantially improve the retrieval accuracy of a baseline CBIR system using Euclidean distance metric, even with a modest amount of log data. The experiment also indicates that the new algorithm is more effective and more efficient than two alternative algorithms, which exploit log data for image retrieval.     

Neighborhood preserving regression for image retrieval

In content-based image retrieval (CBIR), relevance feedback has been proven to be a powerful tool for bridging the gap between low level visual features and high level semantic concepts. Traditionally, relevance feedback driven CBIR is often considered as a supervised learning problem where the user provided feedbacks are used to learn a distance metric or classification function. However, CBIR is intrinsically a semi-supervised learning problem in which the testing samples (images in the database) are present during the learning process. Moreover, when there are no sufficient feedbacks, these methods may suffer from the overfitting problem. In this paper, we propose a novel neighborhood preserving regression algorithm which makes efficient use of both labeled and unlabeled images. By using the unlabeled images, the geometrical structure of the image space can be incorporated into the learning system through a regularizer. Specifically, from all the functions which minimize the empirical loss on the labeled images, we select the one which best preserves the local neighborhood structure of the image space. In this way, our method can obtain a regression function which respects both semantic and geometrical structures of the image database. We present experimental evidence suggesting that our algorithm is able to use unlabeled data effectively for image retrieval.     

多任务分段紧凑特征的车辆检索方法

目的 随着公共安全领域中大规模图像监控及视频数据的增长以及智能交通的发展,车辆检索有着极其重要的应用价值。针对已有车辆检索中自动化和智能化水平低、难以获取精确的检索结果等问题,提出一种多任务分段紧凑特征的车辆检索方法,有效利用车辆基本信息的多样性和关联性实现实时检索。方法 首先,利用相关任务之间的联系提高检索精度和细化图像特征,因此构造了一种多任务深度卷积网络分段学习车辆不同属性的哈希码,将图像语义和图像表示相结合,并采用最小化图像编码使学习到的车辆的不同属性特征更具有鲁棒性;然后,选用特征金字塔网络提取车辆图像的实例特征并利用局部敏感哈希再排序方法对提取到的特征进行检索;最后,针对无法获取查询车辆目标图像的特殊情况,采用跨模态辅助检索方法进行检索。结果 提出的检索方法在3个公开数据集上均优于目前主流的检索方法,其中在CompCars数据集上检索精度达到0.966,在VehicleID数据集上检索精度提升至0.862。结论 本文提出的多任务分段紧凑特征的车辆检索方法既能得到最小化图像编码及图像实例特征,还可在无法获取目标检索图像信息时进行跨模态检索,通过实验对比验证了方法的有效性。     

Automatic localization and annotation of facial features using machine learning techniques

Content-based image retrieval (CBIR) systems traditionally find images within a database that are similar to query image using low level features, such as colour histograms. However, this requires a user to provide an image to the system. It is easier for a user to query the CBIR system using search terms which requires the image content to be described by semantic labels. However, finding a relationship between the image features and semantic labels is a challenging problem to solve. This paper aims to discover semantic labels for facial features for use in a face image retrieval system. Face image retrieval traditionally uses global face-image information to determine similarity between images. However little has been done in the field of face image retrieval to use local face-features and semantic labelling. Our work aims to develop a clustering method for the discovery of semantic labels of face-features. We also present a machine learning based face-feature localization mechanism which we show has promise in providing accurate localization.     

面向大规模胸片图像的深度哈希检索

目的 医学图像检索在疾病诊断、医疗教学和辅助症状参考中发挥了重要作用,但由于医学图像类间相似度高、病灶易遗漏以及数据量较大等问题,使得现有哈希方法对病灶区域特征的关注较少,图像检索准确率较低。对此,本文以胸部X-ray图像为例,提出一种面向大规模胸片图像的深度哈希检索网络。方法 在特征学习部分,首先采用ResNet-50作为主干网络对输入图像进行特征提取得到初步特征,将该特征进行细化后获得全局特征;同时将初步特征输入构建的空间注意模块,该注意模块结合了3个描述符用于聚焦胸片图像中的显著区域,将该模块的输出进行细化得到局部特征;最后融合全局特征与局部特征用于后续哈希码优化。在哈希码优化部分,使用定义的二值交叉熵损失、对比损失和正则化损失的联合函数进行优化学习,生成高质量的哈希码用于图像检索。结果 为了验证方法的有效性,在公开的ChestX-ray8和CheXpert数据集上进行对比实验。结果显示,构建空间注意模块有助于关注病灶区域,定义特征融合模块有效避免了信息的遗漏,联合3个损失函数进行优化可以获得高质量哈希码。与当前先进的医学图像检索方法比较,本文方法能够有效提高医学图像检索的准确率...     

密集网络图像哈希检索

目的 为提取可充分表达图像语义信息的图像特征,减少哈希检索中的投影误差,并生成更紧致的二值哈希码,提出一种基于密集网络和改进的监督核哈希方法。方法 用训练优化好的密集网络提取图像的高层语义特征;先对提取到的图像特征进行核主成分分析投影,充分挖掘图像特征中隐含的非线性信息,以减少投影误差,再利用监督核哈希方法对图像特征进行监督学习,将特征映射到汉明空间,生成更紧致的二值哈希码。结果 为验证提出方法的有效性、可拓展性以及高效性,在Paris6K和LUNA16（lung nodule analysis 16）数据集上与其他6种常用哈希方法相比,所提方法在不同哈希码长下的平均检索精度均较高,且在哈希码长为64 bit时,平均检索精度达到最高,分别为89.2%和92.9%;与基于卷积神经网络的哈希算法（convolution neural network Hashing,CNNH）方法相比,所提方法的时间复杂度有所降低。结论 提出一种基于密集网络和改进的监督核哈希方法,提高了图像特征的表达能力和投影精度,具有较好的检索性能和较低的时间复杂度;且所提方法的可拓展性也较好,不仅能够有效应用到彩色图像检索领域,也可以应用在医学灰度图像检索领域。     

面向跨媒体检索的层级循环注意力网络模型

目的 跨媒体检索旨在以任意媒体数据检索其他媒体的相关数据,实现图像、文本等不同媒体的语义互通和交叉检索。然而,"异构鸿沟"导致不同媒体数据的特征表示不一致,难以实现语义关联,使得跨媒体检索面临巨大挑战。而描述同一语义的不同媒体数据存在语义一致性,且数据内部蕴含着丰富的细粒度信息,为跨媒体关联学习提供了重要依据。现有方法仅仅考虑了不同媒体数据之间的成对关联,而忽略了数据内细粒度局部之间的上下文信息,无法充分挖掘跨媒体关联。针对上述问题,提出基于层级循环注意力网络的跨媒体检索方法。方法 首先提出媒体内-媒体间两级循环神经网络,其中底层网络分别建模不同媒体内部的细粒度上下文信息,顶层网络通过共享参数的方式挖掘不同媒体之间的上下文关联关系。然后提出基于注意力的跨媒体联合损失函数,通过学习媒体间联合注意力来挖掘更加精确的细粒度跨媒体关联,同时利用语义类别信息增强关联学习过程中的语义辨识能力,从而提升跨媒体检索的准确率。结果 在2个广泛使用的跨媒体数据集上,与10种现有方法进行实验对比,并采用平均准确率均值MAP作为评价指标。实验结果表明,本文方法在2个数据集上的MAP分别达到了0.469和0.575,超过了所有对比方法。结论 本文提出的层级循环注意力网络模型通过挖掘图像和文本的细粒度信息,能够充分学习图像和文本之间精确跨媒体关联关系,有效地提高了跨媒体检索的准确率。     

Mixture of KL subspaces for relevance feedback

Relevance feedback has recently emerged as a solution to the problem of improving the retrieval performance of an image retrieval system based on low-level information such as color, texture and shape features. Most of the relevance feedback approaches limit the utilization of the user’s feedback to a single search session, performing a short-term learning. In this paper we present a novel approach for short and long term learning, based on the definition of an adaptive similarity metric and of a high level representation of the images. For short-term learning, the relevant and non-relevant information given by the user during the feedback process is employed to create a positive and a negative subspace of the feature space. For long-term learning, the feedback history of all the users is exploited to create and update a representation of the images which is adopted for improving retrieval performance and progressively reducing the semantic gap between low-level features and high-level semantic concepts. The experimental results prove that the proposed method outperforms many other state of art methods in the short-term learning, and demonstrate the efficacy of the representation adopted for the long-term learning.

跨数据集评估的高光谱图像分类

目的 随着高光谱成像技术的飞速发展,高光谱数据的应用越来越广泛,各场景高光谱图像的应用对高精度详细标注的需求也越来越旺盛。现有高光谱分类模型的发展大多集中于有监督学习,大多数方法都在单个高光谱数据立方中进行训练和评估。由于不同高光谱数据采集场景不同且地物类别不一致,已训练好的模型并不能直接迁移至新的数据集得到可靠标注,这也限制了高光谱图像分类模型的进一步发展。本文提出跨数据集对高光谱分类模型进行训练和评估的模式。方法 受零样本学习的启发,本文引入高光谱类别标签的语义信息,拟通过将不同数据集的原始数据及标签信息分别映射至同一特征空间以建立已知类别和未知类别的关联,再通过将训练数据集的两部分特征映射至统一的嵌入空间学习高光谱图像视觉特征和类别标签语义特征的对应关系,即可将该对应关系应用于测试数据集进行标签推理。结果 实验在一对同传感器采集的数据集上完成,比较分析了语义—视觉特征映射和视觉—语义特征映射方向,对比了5种基于零样本学习的特征映射方法,在高光谱图像分类任务中实现了对分类模型在不同数据集上的训练和评估。结论 实验结果表明,本文提出的基于零样本学习的高光谱分类模型可以实现跨数据集对分类模型进行训练和评估,在高光谱图像分类任务中具有一定的发展潜力。     

残差密集空间金字塔网络的城市遥感图像分割

目的 遥感图像语义分割是根据土地覆盖类型对图像中每个像素进行分类,是遥感图像处理领域的一个重要研究方向。由于遥感图像包含的地物尺度差别大、地物边界复杂等原因,准确提取遥感图像特征具有一定难度,使得精确分割遥感图像比较困难。卷积神经网络因其自主分层提取图像特征的特点逐步成为图像处理领域的主流算法,本文将基于残差密集空间金字塔的卷积神经网络应用于城市地区遥感图像分割,以提升高分辨率城市地区遥感影像语义分割的精度。方法 模型将带孔卷积引入残差网络,代替网络中的下采样操作,在扩大特征图感受野的同时能够保持特征图尺寸不变;模型基于密集连接机制级联空间金字塔结构各分支,每个分支的输出都有更加密集的感受野信息;模型利用跳线连接跨层融合网络特征,结合网络中的高层语义特征和低层纹理特征恢复空间信息。结果 基于ISPRS （International Society for Photogrammetry and Remote Sensing） Vaihingen地区遥感数据集展开充分的实验研究,实验结果表明,本文模型在6种不同的地物分类上的平均交并比和平均F₁值分别达到69.88%和81.39%,性能在数学指标和视觉效果上均优于SegNet、pix2pix、Res-shuffling-Net以及SDFCN （symmetrical dense-shortcut fully convolutional network）算法。结论 将密集连接改进空间金字塔池化网络应用于高分辨率遥感图像语义分割,该模型利用了遥感图像不同尺度下的特征、高层语义信息和低层纹理信息,有效提升了城市地区遥感图像分割精度。     

基于特征互补率矩阵的图像分类方法

在基于内容的图像检索和分类系统中,图像的底层特征和高层语义之间存在着语义鸿沟,有效减小语义鸿沟是一个需要广泛研究的问题。为此,提出一种基于特征互补率矩阵的图像分类方法,该方法通过计算视觉特征互补率矩阵进而指导融合特征集的选择,利用测度学习算法得到一个合适的距离测度以反映图像高层语义的相似度。实验结果表明,该方法能有效提高图像分类精度。     

A Multi-View Embedding Space for Modeling Internet Images,Tags, and Their Semantics

This paper investigates the problem of modeling Internet images and associated text or tags for tasks such as image-to-image search, tag-to-image search, and image-to-tag search (image annotation). We start with canonical correlation analysis (CCA), a popular and successful approach for mapping visual and textual features to the same latent space, and incorporate a third view capturing high-level image semantics, represented either by a single category or multiple non-mutually-exclusive concepts. We present two ways to train the three-view embedding: supervised, with the third view coming from ground-truth labels or search keywords; and unsupervised, with semantic themes automatically obtained by clustering the tags. To ensure high accuracy for retrieval tasks while keeping the learning process scalable, we combine multiple strong visual features and use explicit nonlinear kernel mappings to efficiently approximate kernel CCA. To perform retrieval, we use a specially designed similarity function in the embedded space, which substantially outperforms the Euclidean distance. The resulting system produces compelling qualitative results and outperforms a number of two-view baselines on retrieval tasks on three large-scale Internet image datasets.     

面向细粒度图像的数据关联代理损失

现有度量学习方法中基于元组的损失训练速度慢、基于代理的损失未考虑数据间细粒度的语义关系.针对这些问题,结合两者的优势提出了一种面向细粒度图像的数据关联代理损失(data relation proxy loss,DRPLoss)函数.采用具有批量归一化(BN)层的inception网络作为嵌入网络,在度量空间中利用梯度相互交互学习数据间的相关关系,并使用温度缩放调节DRPLoss对嵌入向量进行监督训练.在CUB-200-2011和Car-196数据集上验证了不同嵌入维度的DRPLoss的有效性,recall@1评价指标分别提升了2％和6.4％.实验结果表明,相比基于元组的损失和基于代理的损失,DRPLoss的训练速度更快,对细粒度图像检索的性能有显著性提高.     

混合生成式和判别式模型的图像自动标注

目的 由于图像检索中存在着低层特征和高层语义之间的“语义鸿沟”,图像自动标注成为当前的关键性问题.为缩减语义鸿沟,提出了一种混合生成式和判别式模型的图像自动标注方法.方法 在生成式学习阶段,采用连续的概率潜在语义分析模型对图像进行建模,可得到相应的模型参数和每幅图像的主题分布.将这个主题分布作为每幅图像的中间表示向量,那么图像自动标注的问题就转化为一个基于多标记学习的分类问题.在判别式学习阶段,使用构造集群分类器链的方法对图像的中间表示向量进行学习,在建立分类器链的同时也集成了标注关键词之间的上下文信息,因而能够取得更高的标注精度和更好的检索效果.结果 在两个基准数据集上进行的实验表明,本文方法在Corel5k数据集上的平均精度、平均召回率分别达到0.28和0.32,在IAPR-TC12数据集上则达到0.29和0.18,其性能优于大多数当前先进的图像自动标注方法.此外,从精度—召回率曲线上看,本文方法也优于几种典型的具有代表性的标注方法.结论 提出了一种基于混合学习策略的图像自动标注方法,集成了生成式模型和判别式模型各自的优点,并在图像语义检索的任务中表现出良好的有效性和鲁棒性.本文方法和技术不仅能应用于图像检索和识别的领域,经过适当的改进之后也能在跨媒体检索和数据挖掘领域发挥重要作用.     

Relevance Feedback and Learning in Content-Based Image Search

A major bottleneck in content-based image retrieval (CBIR) systems or search engines is the large gap between low-level image features used to index images and high-level semantic contents of images. One solution to this bottleneck is to apply relevance feedback to refine the query or similarity measures in image search process. In this paper, we first address the key issues involved in relevance feedback of CBIR systems and present a brief overview of a set of commonly used relevance feedback algorithms. Almost all of the previously proposed methods fall well into such framework. We present a framework of relevance feedback and semantic learning in CBIR. In this framework, low-level features and keyword annotations are integrated in image retrieval and in feedback processes to improve the retrieval performance. We have also extended framework to a content-based web image search engine in which hosting web pages are used to collect relevant annotations for images and users' feedback logs are used to refine annotations. A prototype system has developed to evaluate our proposed schemes, and our experimental results indicated that our approach outperforms traditional CBIR system and relevance feedback approaches.     

结合深度学习与相关反馈的遥感图像检索

目的 针对基于内容的图像检索存在低层视觉特征与用户对图像理解的高层语义不一致、图像检索的精度较低以及传统的分类方法准确度低等问题，提出一种基于卷积神经网络和相关反馈支持向量机的遥感图像检索方法。方法 通过对比度受限直方图均衡化算法对遥感图像进行预处理，限制遥感图像噪声的放大，采用自学习能力良好的卷积神经网络对遥感图像进行多层神经网络的监督学习提取丰富的图像特征，并将支持向量机作为基分类器，根据测试样本数据到分类超平面的距离进行排序得到检索结果，最后采用相关反馈策略对检索结果进行重新调整。结果 在UC Merced Land-Use遥感图像数据集上进行图像检索实验，在mAP（mean average precision）精度指标上，当检索返回图像数为100时，本文方法比LSH（locality sensitive Hashing）方法提高了29.4%，比DSH（density sensitive Hashing）方法提高了37.2%，比EMR（efficient manifold ranking）方法提高了68.8%，比未添加反馈和训练集筛选的SVM（support vector machine）方法提高了3.5%，对于平均检索速度，本文方法比对比方法中mAP精度最高的方法提高了4倍，针对复杂的遥感图像数据，本文方法的检索效果较其他方法表现出色。结论 本文提出了一种以距离评价标准为核心的反馈策略，以提高检索精度，并采用多距离结合的Top-k排序方法合理筛选训练集，以提高检索速度，本文方法可以广泛应用于人脸识别和目标跟踪等领域，对提升检索性能具有重要意义。