Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
Beijing University of Posts and Telecommunications（北京邮电大学）；University of Washington（华盛顿大学）；China Telecom Digital Intelligence Technology Co., Ltd.（中国电信数字智能科技有限公司）
There are two popular loss functions used for vision-language retrieval, i.e., triplet loss and contrastive learning loss, both of them essentially minimize the difference between the similarities of negative pairs and positive pairs. More specifically, Triplet loss with Hard Negative mining (Triplet-HN), which is widely used in existing retrieval models to improve the discriminative ability, is easy to fall into local minima in training. On the other hand, Vision-Language Contrastive learning loss (VLC), which is widely used in the vision-language pre-training, has been shown to achieve significant performance gains on vision-language retrieval, but the performance of fine-tuning with VLC on small datasets is not satisfactory. This paper proposes a unified loss of pair similarity optimization for vision-language retrieval, providing a powerful tool for understanding existing loss functions. Our unified loss includes the hard sample mining strategy of VLC and introduces the margin used by the triplet loss for better similarity separation. It is shown that both Triplet-HN and VLC are special forms of our unified loss. Compared with the Triplet-HN, our unified loss has a fast convergence speed. Compared with the VLC, our unified loss is more discriminative and can provide better generalization in downstream fine-tuning tasks. Experiments on image-text and video-text retrieval benchmarks show that our unified loss can significantly improve the performance of the state-of-the-art retrieval models.
Zhejiang University（浙江大学）；Zhejiang Gongshang University（浙江工商大学）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）
This paper aims for the language-based product image retrieval task. The majority of previous works have made significant progress by designing network structure, similarity measurement, and loss function. However, they typically perform vision-text matching at certain granularity regardless of the intrinsic multiple granularities of images. In this paper, we focus on the cross-modal similarity measurement, and propose a novel Hierarchical Similarity Learning (HSL) network. HSL first learns multi-level representations of input data by stacked encoders, and object-granularity similarity and ima…
Measuring visual similarity between two or more instances within a data distribution is a fundamental task in image retrieval. Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system. In this work, we explore neural networks models for learning a non-metric similarity function for instance search. We argue that non-metric similarity functions based on neural networks can build a better model of human visual perception than standard metric dista…
University of Bristol（布里斯托尔大学）；University of Amsterdam（阿姆斯特丹大学）
Current video retrieval efforts all found their evaluation on an instance-based assumption, that only a single caption is relevant to a query video and vice versa. We demonstrate that this assumption results in performance comparisons often not indicative of models' retrieval capabilities. We propose a move to semantic similarity video retrieval, where (i) multiple videos/captions can be deemed equally relevant, and their relative ranking does not affect a method's reported performance and (ii) retrieved videos/captions are ranked by their similarity to a query. We propose several proxies to e…
Wuhan University（武汉大学）；Brookhaven National Laboratory（布鲁克海文国家实验室）；Sun Yat-Sen University（中山大学）；University of South Carolina（南卡罗来纳大学）；Tianjin University（天津大学）
Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Recently, many deep hashing methods have been proposed and shown largely improved performance over traditional feature-learning-based methods. Most of these methods examine the pairwise similarity on the semantic-level labels, where the pairwise similarity is generally defined in a hard-assignment way. That is, the pairwise similarity is '1' if they share no less than one class label and '0' if they do not share any. However, such similarity definition cannot reflect the similarity rank…
Jinan University（暨南大学）；Beihang University（北京航空航天大学）；Beijing Institute of Technology（北京理工大学）
Image retrieval systems help users to browse and search among extensive images in real-time. With the rise of cloud computing, retrieval tasks are usually outsourced to cloud servers. However, the cloud scenario brings a daunting challenge of privacy protection as cloud servers cannot be fully trusted. To this end, image-encryption-based privacy-preserving image retrieval schemes have been developed, which first extract features from cipher-images, and then build retrieval models based on these features. Yet, most existing approaches extract shallow features and design trivial retrieval models…
We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments. Given a baseline algorithm for measuring the similarity of two face sets, the meta-algorithm introduced in this paper seeks to leverage the structure of the data corpus to make the best use of the available baseline. In particular, we show how partial transitivity of inter-personal similarity can be exploited to improve the retrieval of particularly challenging sets which poorly match the query under the baseline measure. We: (i) describe the use of proxy sets as …
Huazhong University of Science and Technology（华中科技大学）；Huawei Cloud & AI（华为云与人工智能）
Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by matching a query text to the recognized words, outputted by an end-to-end scene text spotter. In this paper, we address this problem by directly learning a cross-modal similarity between a query text and each text instance from natural images. Specifically, we establish an end-to-end trainable network, jointly optimizing the procedures of scene text detection and cross-modal similarity learning. In this way, scene tex…
AI Technology Center, Online-Video BU, Tencent（腾讯在线视频事业部AI技术中心）
As a basic task of computer vision, image similarity retrieval is facing the challenge of large-scale data and image copy attacks. This paper presents our 3rd place solution to the matching track of Image Similarity Challenge (ISC) 2021 organized by Facebook AI. We propose a multi-branch retrieval method of combining global descriptors and local descriptors to cover all attack cases. Specifically, we attempt many strategies to optimize global descriptors, including abundant data augmentations, self-supervised learning with a single Transformer model, overlay detection preprocessing. Moreover, …
Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）；Chinese Academy of Sciences（中国科学院）
Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distribution. For multi-label image retrieval, however, previous methods only use multiple hash centers with equal weights to generate one centroid as the learning target, which ignores the relationship between the weights of hash centers and the proportion of instance regions in the image. To address the …
As a scene graph compactly summarizes the high-level content of an image in a structured and symbolic manner, the similarity between scene graphs of two images reflects the relevance of their contents. Based on this idea, we propose a novel approach for image-to-image retrieval using scene graph similarity measured by graph neural networks. In our approach, graph neural networks are trained to predict the proxy image relevance measure, computed from human-annotated captions using a pre-trained sentence similarity model. We collect and publish the dataset for image relevance measured by human a…
National University of Singapore（新加坡国立大学）；Tencent AI Lab（腾讯人工智能实验室）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Existing data-dependent hashing methods usually learn hash functions from pairwise or triplet data relationships, which only capture the data similarity locally, and often suffer from low learning efficiency and low collision rate. In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy. We principally formulate the computation of the pro…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Centerfield Corporation（Centerfield公司）；Cornell University（康奈尔大学）；Shandong Medical College（山东医学高等专科学校）；New York University Abu Dhabi（纽约大学阿布扎比分校）；Soochow University（苏州大学）；California State University San Bernardino（加州州立大学圣贝纳迪诺分校）；Travelers Canada（旅行者加拿大公司）
In this paper we study the problem of content-based image retrieval. In this problem, the most popular performance measure is the top precision measure, and the most important component of a retrieval system is the similarity function used to compare a query image against a database image. However, up to now, there is no existing similarity learning method proposed to optimize the top precision measure. To fill this gap, in this paper, we propose a novel similarity learning method to maximize the top precision measure. We model this problem as a minimization problem with an objective function …
Beijing University of Posts and Telecommunications（北京邮电大学）；Raytheon BBN Technologies（雷神BBN技术公司）；Tianjing University（天津大学）
To effectively retrieve objects from large corpus with high accuracy is a challenge task. In this paper, we propose a method that propagates visual feature level similarities on a Markov random field (MRF) to obtain a high level correspondence in image space for image pairs. The proposed correspondence between image pair reflects not only the similarity of low-level visual features but also the relations built through other images in the database and it can be easily integrated into the existing bag-of-visual-words(BoW) based systems to reduce the missing rate. We evaluate our method on the st…
Face image retrieval, which searches for images of the same identity from the query input face image, is drawing more attention as the size of the image database increases rapidly. In order to conduct fast and accurate retrieval, a compact hash code-based methods have been proposed, and recently, deep face image hashing methods with supervised classification training have shown outstanding performance. However, classification-based scheme has a disadvantage in that it cannot reveal complex similarities between face images into the hash code learning. In this paper, we attempt to improve the fa…
Cluster-Aware Similarity Diffusion for Instance Retrieval
University of Science and Technology of China（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Department of Electrical Engineering and Computer Sciences（电气工程与计算机科学系）；University of California, Berkeley（加州大学伯克利分校）
Recent advances in computer graphics and computer vision have found successful application of deep neural network models for 3D shapes based on signed distance functions (SDFs) that are useful for shape representation, retrieval, and completion. However, this approach has been limited by the need to have query shapes in the same canonical scale and pose as those observed during training, restricting its effectiveness on real world scenes. We present a formulation to overcome this issue by jointly estimating shape and similarity transform parameters. We conduct experiments to demonstrate the ef…
In this paper, we introduce 3D-CSL, a compact pipeline for Near-Duplicate Video Retrieval (NDVR), and explore a novel self-supervised learning strategy for video similarity learning. Most previous methods only extract video spatial features from frames separately and then design kinds of complex mechanisms to learn the temporal correlations among frame features. However, parts of spatiotemporal dependencies have already been lost. To address this, our 3D-CSL extracts global spatiotemporal dependencies in videos end-to-end with a 3D transformer and find a good balance between efficiency and eff…
Deep supervised hashing for image retrieval has attracted researchers' attention due to its high efficiency and superior retrieval performance. Most existing deep supervised hashing works, which are based on pairwise/triplet labels, suffer from the expensive computational cost and insufficient utilization of the semantics information. Recently, deep classwise hashing introduced a classwise loss supervised by class labels information alternatively; however, we find it still has its drawback. In this paper, we propose an improved deep classwise hashing, which enables hashing learning and class c…
Ocean University of China（中国海洋大学）；Nanjing University（南京大学）
Image retrieval has been a top topic in the field of both computer vision and machine learning for a long time. Content based image retrieval, which tries to retrieve images from a database visually similar to a query image, has attracted much attention. Two most important issues of image retrieval are the representation and ranking of the images. Recently, bag-of-words based method has shown its power as a representation method. Moreover, nonnegative matrix factorization is also a popular way to represent the data samples. In addition, contextual similarity learning has also been studied and …
A novel solution for the content-based 3D shape retrieval problem using an unsupervised clustering approach, which does not need any label information of 3D shapes, is presented in this work. The proposed shape retrieval system consists of two modules in cascade: the irrelevance filtering (IF) module and the similarity ranking (SR) module. The IF module attempts to cluster gallery shapes that are similar to each other by examining global and local features simultaneously. However, shapes that are close in the local feature space can be distant in the global feature space, and vice versa. To re…
SenseTime Research（商汤科技研究院）；Sun Yat-sen University（中山大学）；The University of Hong Kong（香港大学）
Matching clothing images from customers and online shopping stores has rich applications in E-commerce. Existing algorithms encoded an image as a global feature vector and performed retrieval with the global representation. However, discriminative local information on clothes are submerged in this global representation, resulting in sub-optimal performance. To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales. The similari…
Sun Yat-sen University（中山大学）；Guangdong University of Foreign Studies（广东外语外贸大学）；Western Kentucky University（西肯塔基大学）；Guilin University of Electronic Technology（桂林电子科技大学）
Fabric image retrieval is beneficial to many applications including clothing searching, online shopping and cloth modeling. Learning pairwise image similarity is of great importance to an image retrieval task. With the resurgence of Convolutional Neural Networks (CNNs), recent works have achieved significant progresses via deep representation learning with metric embedding, which drives similar examples close to each other in a feature space, and dissimilar ones apart from each other. In this paper, we propose a novel embedding method termed focus ranking that can be easily unified into a CNN …
We present a deep learning approach for learning the joint semantic embeddings of images and captions in a Euclidean space, such that the semantic similarity is approximated by the L2 distances in the embedding space. For that, we introduce a metric learning scheme that utilizes multitask learning to learn the embedding of identical semantic concepts using a center loss. By introducing a differentiable quantization scheme into the end-to-end trainable network, we derive a semantic embedding of semantically similar concepts in Euclidean space. We also propose a novel metric learning formulation…
Zhejiang University（浙江大学）；Renmin University of China（中国人民大学）
In order to retrieve unlabeled images by textual queries, cross-media similarity computation is a key ingredient. Although novel methods are continuously introduced, little has been done to evaluate these methods together with large-scale query log analysis. Consequently, how far have these methods brought us in answering real-user queries is unclear. Given baseline methods that compute cross-media similarity using relatively simple text/image matching, how much progress have advanced models made is also unclear. This paper takes a pragmatic approach to answering the two questions. Queries are…
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
In content-based image retrieval, the first-round retrieval result by simple visual feature comparison may be unsatisfactory, which can be refined by visual re-ranking techniques. In image retrieval, it is observed that the contextual similarity among the top-ranked images is an important clue to distinguish the semantic relevance. Inspired by this observation, in this paper, we propose a visual re-ranking method by contextual similarity aggregation with self-attention. In our approach, for each image in the top-K ranking list, we represent it into an affinity feature vector by comparing it wi…
Lesion images are frequently taken in open-set settings. Because of this, the image data generated is extremely varied in nature.It is difficult for a convolutional neural network to find proper features and generalise well, as a result content based image retrieval (CBIR) system for lesion images are difficult to build. This paper explores this domain and proposes multiple similarity measures which uses Style Loss and Dice Coefficient via a novel similarity measure called I1-Score. Out of the CBIR similarity measures proposed, pure style loss approach achieves a remarkable accuracy increase o…
Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers for generating image descriptors and train the resulting model with a metric learning objective, which combines a contrastive loss with a differential entropy regularizer. Our results show consistent and significant improvements of transformers over convolution-based approaches. In particular, our method outperforms the state of the art on several public be…
Product retrieval is of great importance in the ecommerce domain. This paper introduces our 1st-place solution in eBay eProduct Visual Search Challenge (FGVC9), which is featured for an ensemble of about 20 models from vision models and vision-language models. While model ensemble is common, we show that combining the vision models and vision-language models brings particular benefits from their complementarity and is a key factor to our superiority. Specifically, for the vision models, we use a two-stage training pipeline which first learns from the coarse labels provided in the training set …
Hue University（顺化大学）；HoChiMinh city University of Food Industry（胡志明市食品工业大学）
The paper approaches the binary signature for each image based on the percentage of the pixels in each color images, at the same time the paper builds a similar measure between images based on EMD (Earth Mover's Distance). Besides, the paper proceeded to create the S-tree based on the similar measure EMD to store the image's binary signatures to quickly query image signature data. From there, the paper build an image retrieval algorithm and CBIR (Content-Based Image Retrieval) based on a similar measure EMD and S-tree. Based on this theory, the paper proceeded to build application and experime…
Indian Institute of Information Technology, Allahabad（阿拉哈巴德印度信息技术学院）；National Cheng Kung University（国立成功大学）
Deep learning has shown a tremendous growth in hashing techniques for image retrieval. Recently, Transformer has emerged as a new architecture by utilizing self-attention without convolution. Transformer is also extended to Vision Transformer (ViT) for the visual recognition with a promising performance on ImageNet. In this paper, we propose a Vision Transformer based Hashing (VTS) for image retrieval. We utilize the pre-trained ViT on ImageNet as the backbone network and add the hashing head. The proposed VTS model is fine tuned for hashing under six different image retrieval frameworks, incl…
Beijing University of Posts and Telecommunications（北京邮电大学）；Tencent PCG（腾讯平台与内容事业群）；Tianjin University（天津大学）
The current state-of-the-art methods for video corpus moment retrieval (VCMR) often use similarity-based feature alignment approach for the sake of convenience and speed. However, late fusion methods like cosine similarity alignment are unable to make full use of the information from both query texts and videos. In this paper, we combine feature alignment with feature fusion to promote the performance on VCMR.
National Institute of Standards and Technology（美国国家标准与技术研究院）
In this paper, we describe a framework for similarity based retrieval and clustering from a 3D human database. Our technique is based on both body and head shape representation and the retrieval is based on similarity of both of them. The 3D human database used in our study is the CAESAR anthropometric database which contains approximately 5000 bodies. We have developed a web-based interface for specifying the queries to interact with the retrieval system. Our approach performs the similarity based retrieval in a reasonable amount of time and is a practical approach.
Video-text retrieval has been a crucial and fundamental task in multi-modal research. The development of video-text retrieval has been considerably promoted by large-scale multi-modal contrastive pre-training, which primarily focuses on coarse-grained or fine-grained contrast. However, cross-grained contrast, which is the contrast between coarse-grained representations and fine-grained representations, has rarely been explored in prior research. Compared with fine-grained or coarse-grained contrasts, cross-grained contrast calculate the correlation between coarse-grained features and each fine…
Shanghai Jiao Tong University（上海交通大学）；University of Cambridge（剑桥大学）
Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of environmental conditions, e.g. illumination, seasonal and weather changes, retrieval-based visual localization is severely affected and becomes a challenging problem. In this work, a general architecture is first formulated probabilistically to extract domain invariant feature through multi-domain image translation. And then a novel gradient-weighted similarity activat…
Adaptive Cortically Constrained EEG-Vision Alignment for Zero-Shot Brain-to-Image Retrieval
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Shanghai Jiaotong University（上海交通大学）；Chongqing Normal University（重庆师范大学）；South China University of Technology（华南理工大学）
City University of Hong Kong（香港城市大学）；Tencent AI Lab（腾讯人工智能实验室）；Shenzhen University（深圳大学）
Deep hashing models have been proposed as an efficient method for large-scale similarity search. However, most existing deep hashing methods only utilize fine-level labels for training while ignoring the natural semantic hierarchy structure. This paper presents an effective method that preserves the classwise similarity of full-level semantic hierarchy for large-scale image retrieval. Experiments on two benchmark datasets show that our method helps improve the fine-level retrieval performance. Moreover, with the help of the semantic hierarchy, it can produce significantly better binary codes f…
Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders
King Abdullah University of Science and Technology（国王阿卜杜勒-阿齐兹大学科学与技术大学）；Visual Recognition Group（视觉识别组）；Faculty of Electrical Engineering（电气工程学院）；Czech Technical University in Prague（布拉格捷克技术大学）
University of Michigan（密歇根大学）；University of Washington（华盛顿大学）；The Hebrew University（希伯来大学）
We study a realization of motion and similarity group equivalence classes of $n\geq 1$ labeled points in $\mathbb R^k,\, k\geq 1$ as a metric space with a computable metric. Our study is motivated by applications in computer vision.
Boston University（波士顿大学）；University of British Columbia（英属哥伦比亚大学）
We address the problem of text-based activity retrieval in video. Given a sentence describing an activity, our task is to retrieve matching clips from an untrimmed video. To capture the inherent structures present in both text and video, we introduce a multilevel model that integrates vision and language features earlier and more tightly than prior work. First, we inject text features early on when generating clip proposals, to help eliminate unlikely clips and thus speed up processing and boost performance. Second, to learn a fine-grained similarity metric for retrieval, we use visual feature…
GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features
School of Physics and Electronics, Hubei Normal University（湖北师范大学物理与电子科学学院）；School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）
MIRACL-VISION: A Large, multilingual, visual document retrieval benchmark
The Thørväld Group（Thørväld集团）；Inria Paris-Rocquencourt（巴黎-罗克琴库尔Inria）；Rajiv Gandhi University Doimukh（拉朱·甘地大学多伊穆克）；Tsinghua University（清华大学）；Palmer Research Laboratories（Palmer研究实验室）；The Kumquat Consortium（Kumquat联盟）
