Discovery of a perceptual distance function for measuring image similarity

For more than a decade, researchers have actively explored the area of image/video analysis and retrieval. Yet one fundamental problem remains largely unsolved: how to measure perceptual similarity between two objects. For this purpose, most researchers employ a Minkowski-type metric. Unfortunately, the Minkowski metric does not reliably find similarities in objects that are obviously alike. Through mining a large set of visual data, our team has discovered a perceptual distance function. We call the discovered function the dynamic partial function (DPF). When we empirically compare DPF to Minkowski-type distance functions in image retrieval and in video shot-transition detection using our image features, DPF performs significantly better. The effectiveness of DPF can be explained by similarity theories in cognitive psychology.     

Fast Similarity Search for Learned Metrics

We introduce a method that enables scalable similarity search for learned metrics. Given pairwise similarity and dissimilarity constraints between some examples, we learn a Mahalanobis distance function that captures the examples' underlying relationships well. To allow sublinear time similarity search under the learned metric, we show how to encode the learned metric parameterization into randomized locality-sensitive hash functions. We further formulate an indirect solution that enables metric learning and hashing for vector spaces whose high dimensionality makes it infeasible to learn an explicit transformation over the feature dimensions. We demonstrate the approach applied to a variety of image data sets, as well as a systems data set. The learned metrics improve accuracy relative to commonly used metric baselines, while our hashing construction enables efficient indexing with learned distances and very large databases.     

Learning multi-task local metrics for image annotation

The goal of image annotation is to automatically assign a set of textual labels to an image to describe the visual contents thereof. Recently, with the rapid increase in the number of web images, nearest neighbor (NN) based methods have become more attractive and have shown exciting results for image annotation. One of the key challenges of these methods is to define an appropriate similarity measure between images for neighbor selection. Several distance metric learning (DML) algorithms derived from traditional image classification problems have been applied to annotation tasks. However, a fundamental limitation of applying DML to image annotation is that it learns a single global distance metric over the entire image collection and measures the distance between image pairs in the image-level. For multi-label annotation problems, it may be more reasonable to measure similarity of image pairs in the label-level. In this paper, we develop a novel label prediction scheme utilizing multiple label-specific local metrics for label-level similarity measure, and propose two different local metric learning methods in a multi-task learning (MTL) framework. Extensive experimental results on two challenging annotation datasets demonstrate that 1) utilizing multiple local distance metrics to learn label-level distances is superior to using a single global metric in label prediction, and 2) the proposed methods using the MTL framework to learn multiple local metrics simultaneously can model the commonalities of labels, thereby facilitating label prediction results to achieve state-of-the-art annotation performance.     

一种基于内容相关性的跨媒体检索方法

针对传统基于内容的多媒体检索对单一模态的限制,提出一种新的跨媒体检索方法.分析了不同模态的内容特征之间在统计意义上的典型相关性,并通过子空间映射解决了特征向量的异构性问题,同时结合相关反馈中的先验知识,修正不同模态多媒体数据集在子空间中的拓扑结构,实现跨媒体相关性的准确度量.实验以图像和音频数据为例验证了基于相关性学习的跨媒体检索方法的有效性.     

Cross-media similarity metric learning with unified deep networks

As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important to boost the cross-media retrieval. Motivated by the strong ability of deep neural network in feature representation and comparison functions learning, we propose the Unified Network for Cross-media Similarity Metric (UNCSM) to associate cross-media shared representation learning with distance metric in a unified framework. First, we design a two-pathway deep network pretrained with contrastive loss, and employ double triplet similarity loss for fine-tuning to learn the shared representation for each media type by modeling the relative semantic similarity. Second, the metric network is designed for effectively calculating the cross-media similarity of the shared representation, by modeling the pairwise similar and dissimilar constraints. Compared to the existing methods which mostly ignore the dissimilar constraints and only use sample distance metric as Euclidean distance separately, our UNCSM approach unifies the representation learning and distance metric to preserve the relative similarity as well as embrace more complex similarity functions for further improving the cross-media retrieval accuracy. The experimental results show that our UNCSM approach outperforms 8 state-of-the-art methods on 4 widely-used cross-media datasets.

     

Towards Data-Adaptive and User-Adaptive Image Retrieval by Peer Indexing

Adaptation to the characteristics of specific images and the preferences of individual users is critical to the success of an image retrieval system but insufficiently addressed by the existing approaches. In this paper, we propose an elegant and effective approach to data-adaptive and user-adaptive image retrieval based on the idea of peer indexing—describing an image through semantically relevant peer images. Specifically, we associate each image with a two-level peer index that models the “data characteristics” of the image as well as the “user characteristics” of individual users with respect to this image. Based on two-level image peer indexes, a set of retrieval parameters including query vectors and similarity metric are optimized towards both data and user characteristics by applying the pseudo feedback strategy. A cooperative framework is proposed under which peer indexes and image visual features are integrated to facilitate data- and user-adaptive image retrieval. Simulation experiments conducted on real-world images have verified the effectiveness of our approach in a relatively restricted setting.     

Efficient Content-Based Image Retrieval through Metric Histograms

This paper presents a new and efficient method for content-based image retrieval employing the color distribution of images. This new method, called metric histogram, takes advantage of the correlation among adjacent bins of histograms, reducing the dimensionality of the feature vectors extracted from images, leading to faster and more flexible indexing and retrieval processes. The proposed technique works on each image independently from the others in the dataset, therefore there is no pre-defined number of color regions in the resulting histogram. Thus, it is not possible to use traditional comparison algorithms such as Euclidean or Manhattan distances. To allow the comparison of images through the new feature vectors given by metric histograms, a new metric distance function MHD( ) is also proposed. This paper shows the improvements in timing and retrieval discrimination obtained using metric histograms over traditional ones, even when using images with different spatial resolution or thumbnails. The experimental evaluation of the new method, for answering similarity queries over two representative image databases, shows that the metric histograms surpass the retrieval ability of traditional histograms because they are invariant on geometrical and brightness image transformations, and answer the queries up to 10 times faster than the traditional ones.     

Learning similarity measure for natural image retrieval with relevance feedback

A new scheme of learning similarity measure is proposed for content-based image retrieval (CBIR). It learns a boundary that separates the images in the database into two clusters. Images inside the boundary are ranked by their Euclidean distances to the query. The scheme is called constrained similarity measure (CSM), which not only takes into consideration the perceptual similarity between images, but also significantly improves the retrieval performance of the Euclidean distance measure. Two techniques, support vector machine (SVM) and AdaBoost from machine learning, are utilized to learn the boundary. They are compared to see their differences in boundary learning. The positive and negative examples used to learn the boundary are provided by the user with relevance feedback. The CSM metric is evaluated in a large database of 10009 natural images with an accurate ground truth. Experimental results demonstrate the usefulness and effectiveness of the proposed similarity measure for image retrieval.     

Locally adaptive subspace and similarity metric learning for visual data clustering and retrieval

Subspace and similarity metric learning are important issues for image and video analysis in the scenarios of both computer vision and multimedia fields. Many real-world applications, such as image clustering/labeling and video indexing/retrieval, involve feature space dimensionality reduction as well as feature matching metric learning. However, the loss of information from dimensionality reduction may degrade the accuracy of similarity matching. In practice, such basic conflicting requirements for both feature representation efficiency and similarity matching accuracy need to be appropriately addressed. In the style of “Thinking Globally and Fitting Locally”, we develop Locally Embedded Analysis (LEA) based solutions for visual data clustering and retrieval. LEA reveals the essential low-dimensional manifold structure of the data by preserving the local nearest neighbor affinity, and allowing a linear subspace embedding through solving a graph embedded eigenvalue decomposition problem. A visual data clustering algorithm, called Locally Embedded Clustering (LEC), and a local similarity metric learning algorithm for robust video retrieval, called Locally Adaptive Retrieval (LAR), are both designed upon the LEA approach, with variations in local affinity graph modeling. For large size database applications, instead of learning a global metric, we localize the metric learning space with kd-tree partition to localities identified by the indexing process. Simulation results demonstrate the effective performance of proposed solutions in both accuracy and speed aspects.     

Improved multidimensional scaling analysis using neural networks with distance-error backpropagation

We show that neural networks, with a suitable error function for backpropagation, can be successfully used for metric multidimensional scaling (MDS) (i.e., dimensional reduction while trying to preserve the original distances between patterns) and are in fact able to outdo the standard algebraic approach to MDS, known as classical scaling.     

Enhancing remote sensing image retrieval using a triplet deep metric learning network

ABSTRACT

With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data. In this letter, we present a novel content-based remote sensing image retrieval (RSIR) method based on Triplet deep metric learning convolutional neural network (CNN). By constructing a Triplet network with metric learning objective function, we extract the representative features of the images in a semantic space in which images from the same class are close to each other while those from different classes are far apart. In such a semantic space, simple metric measures such as Euclidean distance can be used directly to compare the similarity of images and effectively retrieve images of the same class. We also investigate a supervised and an unsupervised learning methods for reducing the dimensionality of the learned semantic features. We present comprehensive experimental results on two public RSIR datasets and show that our method significantly outperforms state-of-the-art.     

Multi-GAT: 基于多度量衡构建图的故障诊断方法

基于图神经网络的故障诊断方法, 通常需要根据度量衡确定样本之间的相似性, 进而构建图的拓扑结构.然而, 根据单一度量衡可能无法准确衡量数据样本之间的相似性, 进而导致无法准确表征样本之间的关系. 因此, 选用不同的度量衡会极大地影响图神经网络的诊断性能. 为了解决通过单一度量衡无法准确表征数据样本之间相关性的问题, 本文提出了一种基于多度量衡构造图的故障诊断模型???Multi-GAT. 通过结合3种度量衡的计算结果,从而判断数据样本之间相关性的强弱. 本文改进了图注意力网络的评分函数, 使其能够依据样本之间相关性的强弱更准确地确定数据样本之间的相似性. 在本文基准数据集上的实验表明, Multi-GAT能够提升模型的诊断精度,且拥有较好的稳定性.     

Ptolemaic access methods: Challenging the reign of the metric space model

Metric indexing is the state of the art in general distance-based retrieval. Relying on the triangular inequality, metric indexes achieve significant online speed-up beyond a linear scan. Recently, the idea of Ptolemaic indexing was introduced, which substitutes Ptolemy's inequality for the triangular one, potentially yielding higher efficiency for the distances where it applies. In this paper we have adapted several metric indexes to support Ptolemaic indexing, thus establishing a class of Ptolemaic access methods (PtoAM). In particular, we include Ptolemaic Pivot tables, Ptolemaic PM-Trees and the Ptolemaic M-Index. We also show that the most important and promising family of distances suitable for Ptolemaic indexing is the signature quadratic form distance, an adaptive similarity measure which can cope with flexible content representations of multimedia data, among other things. While this distance has shown remarkable qualities regarding the search effectiveness, its high computational complexity underscores the need for efficient search methods. We show that these distances are Ptolemaic metrics and present a study where we apply Ptolemaic indexing methods on real-world image databases, resolving exact queries nearly four times as fast as the state-of-the-art metric solution, and up to three orders of magnitude times as fast as sequential scan.     

Product Quantization Network for Fast Visual Search

Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features. By constructing the approximation function, we extend the hard-assignment quantization to soft-assignment quantization. Thanks to the differentiable property of the soft-assignment quantization, the product quantization operation can be integrated as a layer in a convolutional neural network, constructing the proposed product quantization network (PQN). Meanwhile, by extending the triplet loss to the asymmetric triplet loss, we directly optimize the retrieval accuracy of the learned representation based on asymmetric similarity measurement. Utilizing PQN, we can learn a discriminative and compact image representation in an end-to-end manner, which further enables a fast and accurate image retrieval. By revisiting residual quantization, we further extend the proposed PQN to residual product quantization network (RPQN). Benefited from the residual learning triggered by residual quantization, RPQN achieves a higher accuracy than PQN using the same computation cost. Moreover, we extend PQN to temporal product quantization network (TPQN) by exploiting temporal consistency in videos to speed up the video retrieval. It integrates frame-wise feature learning, frame-wise features aggregation and video-level feature quantization in a single neural network. Comprehensive experiments conducted on multiple public benchmark datasets demonstrate the state-of-the-art performance of the proposed PQN, RPQN and TPQN in fast image and video retrieval.

     

Cross-modal alignment with graph reasoning for image-text retrieval

Image-text retrieval task has received a lot of attention in the modern research field of artificial intelligence. It still remains challenging since image and text are heterogeneous cross-modal data. The key issue of image-text retrieval is how to learn a common feature space while semantic correspondence between image and text remains. Existing works cannot gain fine cross-modal feature representation because the semantic relation between local features is not effectively utilized and the noise information is not suppressed. In order to address these issues, we propose a Cross-modal Alignment with Graph Reasoning (CAGR) model, in which the refined cross-modal features in the common feature space are learned and then a fine-grained cross-modal alignment method is implemented. Specifically, we introduce a graph reasoning module to explore semantic connection for local elements in each modality and measure their importance by self-attention mechanism. In a multi-step reasoning manner, the visual semantic graph and textual semantic graph can be effectively learned and the refined visual and textual features can be obtained. Finally, to measure the similarity between image and text, a novel alignment approach named cross-modal attentional fine-grained alignment is used to compute similarity score between two sets of features. Our model achieves the competitive performance compared with the state-of-the-art methods on Flickr30K dataset and MS-COCO dataset. Extensive experiments demonstrate the effectiveness of our model.

     

Spatially aware feature selection and weighting for object retrieval

Many recent image retrieval methods are based on the “bag-of-words” (BoW) model with some additional spatial consistency checking. This paper proposes a more accurate similarity measurement that takes into account spatial layout of visual words in an offline manner. The similarity measurement is embedded in the standard pipeline of the BoW model, and improves two features of the model: i) latent visual words are added to a query based on spatial co-occurrence, to improve query recall; and ii) weights of reliable visual words are increased to improve the precision. The combination of these methods leads to a more accurate measurement of image similarity. This is similar in concept to the combination of query expansion and spatial verification, but does not require query time processing, which is too expensive to apply to full list of ranked results. Experimental results demonstrate the effectiveness of our proposed method on three public datasets.     

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.     

图像检索中的动态相似性度量方法

为提高图像检索的效率,近年来相关反馈机制被引入到了基于内容的图像检索领域。该文提出了一种新的相关反馈方法－－动态相似性度量方法。该方法建立在目前被广泛采用的图像相拟性度量方法的基础上,结合了相关反馈图像检索系统的时序特性,通过捕获用户的交互信息,动态地修正图像的相似性度量公式,从而把用户模型嵌入到了图像检索系统,在某种程度上使图像检索结果与人的主观感知更加接近。实验结果表明该方法的性能明显优于其它图像检索系统所采用的方法。     

Locally linear metric adaptation with application to semi-supervised clustering and image retrieval

Many computer vision and pattern recognition algorithms are very sensitive to the choice of an appropriate distance metric. Some recent research sought to address a variant of the conventional clustering problem called semi-supervised clustering, which performs clustering in the presence of some background knowledge or supervisory information expressed as pairwise similarity or dissimilarity constraints. However, existing metric learning methods for semi-supervised clustering mostly perform global metric learning through a linear transformation. In this paper, we propose a new metric learning method that performs nonlinear transformation globally but linear transformation locally. In particular, we formulate the learning problem as an optimization problem and present three methods for solving it. Through some toy data sets, we show empirically that our locally linear metric adaptation (LLMA) method can handle some difficult cases that cannot be handled satisfactorily by previous methods. We also demonstrate the effectiveness of our method on some UCI data sets. Besides applying LLMA to semi-supervised clustering, we have also used it to improve the performance of content-based image retrieval systems through metric learning. Experimental results based on two real-world image databases show that LLMA significantly outperforms other methods in boosting the image retrieval performance.