Most real world applications of image retrieval such as Adobe Stock, which is a marketplace for stock photography and illustrations, need a way for users to find images which are both visually (i.e. aesthetically) and conceptually (i.e. containing the same salient objects) as a query image. Learning visual-semantic representations from images is a well studied problem for image retrieval. Filtering based on image concepts or attributes is traditionally achieved with index-based filtering (e.g. on textual tags) or by re-ranking after an initial visual embedding based retrieval. In this paper, we learn a joint vision and concept embedding in the same high-dimensional space. This joint model gives the user fine-grained control over the semantics of the result set, allowing them to explore the catalog of images more rapidly. We model the visual and concept relationships as a graph structure, which captures the rich information through node neighborhood. This graph structure helps us learn multi-modal node embeddings using Graph Neural Networks. We also introduce a novel inference time control, based on selective neighborhood connectivity allowing the user control over the retrieval algorithm. We evaluate these multi-modal embeddings quantitatively on the downstream relevance task of image retrieval on MS-COCO dataset and qualitatively on MS-COCO and an Adobe Stock dataset.
This article presents an efficient end-to-end method to perform instance-level recognition employed to the task of labeling and ranking landmark images. In a first step, we embed images in a high dimensional feature space using convolutional neural networks trained with an additive angular margin loss and classify images using visual similarity. We then efficiently re-rank predictions and filter noise utilizing similarity to out-of-domain images. Using this approach we achieved the 1st place in the 2020 edition of the Google Landmark Recognition challenge.
Gray Level Co-occurrence Matrices (GLCM) are one of the earliest techniques used for image texture analysis. In this paper we defined a new feature called trace extracted from the GLCM and its implications in texture analysis are discussed in the context of Content Based Image Retrieval (CBIR). The theoretical extension of GLCM to n-dimensional gray scale images are also discussed. The results indicate that trace features outperform Haralick features when applied to CBIR.
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc. Image retrieval for localization is an efficient and effective solution to the problem. In this paper, we propose a novel multi-task architecture to fuse the geometric and semantic information into the multi-scale latent embedding representation for visual place recognition. To use the high-quality ground truths without any human effort, the effective multi-scale feature discriminator is proposed for adversarial training to achieve the domain adaptation from synthetic virtual KITTI dataset to real-world KITTI dataset. The proposed approach is validated on the Extended CMU-Seasons dataset and Oxford RobotCar dataset through a series of crucial comparison experiments, where our performance outperforms state-of-the-art baselines for retrieval-based localization and large-scale place recognition under the challenging environment.
To better understand scene images in the field of remote sensing, multi-label annotation of scene images is necessary. Moreover, to enhance the performance of deep learning models for dealing with semantic scene understanding tasks, it is vital to train them on large-scale annotated data. However, most existing datasets are annotated by a single label, which cannot describe the complex remote sensing images well because scene images might have multiple land cover classes. Few multi-label high spatial resolution remote sensing datasets have been developed to train deep learning models for multi-label based tasks, such as scene classification and image retrieval. To address this issue, in this paper, we construct a multi-label high spatial resolution remote sensing dataset named MLRSNet for semantic scene understanding with deep learning from the overhead perspective. It is composed of high-resolution optical satellite or aerial images. MLRSNet contains a total of 109,161 samples within 46 scene categories, and each image has at least one of 60 predefined labels. We have designed visual recognition tasks, including multi-label based image classification and image retrieval, in which a wide variety of deep learning approaches are evaluated with MLRSNet. The experimental results demonstrate that MLRSNet is a significant benchmark for future research, and it complements the current widely used datasets such as ImageNet, which fills gaps in multi-label image research. Furthermore, we will continue to expand the MLRSNet. MLRSNet and all related materials have been made publicly available at https://data.mendeley.com/datasets/7j9bv9vwsx/2 and https://github.com/cugbrs/MLRSNet.git.
We present a similar image retrieval (SIR) platform that is used to quickly discover visually similar products in a catalog of millions. Given the size, diversity, and dynamism of our catalog, product search poses many challenges. It can be addressed by building supervised models to tagging product images with labels representing themes and later retrieving them by labels. This approach suffices for common and perennial themes like "white shirt" or "lifestyle image of TV". It does not work for new themes such as "e-cigarettes", hard-to-define ones such as "image with a promotional badge", or the ones with short relevance span such as "Halloween costumes". SIR is ideal for such cases because it allows us to search by an example, not a pre-defined theme. We describe the steps - embedding computation, encoding, and indexing - that power the approximate nearest neighbor search back-end. We also highlight two applications of SIR. The first one is related to the detection of products with various types of potentially objectionable themes. This application is run with a sense of urgency, hence the typical time frame to train and bootstrap a model is not permitted. Also, these themes are often short-lived based on current trends, hence spending resources to build a lasting model is not justified. The second application is a variant item detection system where SIR helps discover visual variants that are hard to find through text search. We analyze the performance of SIR in the context of these applications.
Visual localization to compute 6DoF camera pose from a given image has wide applications such as in robotics, virtual reality, augmented reality, etc. Two kinds of descriptors are important for the visual localization. One is global descriptors that extract the whole feature from each image. The other is local descriptors that extract the local feature from each image patch usually enclosing a key point. More and more methods of the visual localization have two stages: at first to perform image retrieval by global descriptors and then from the retrieval feedback to make 2D-3D point correspondences by local descriptors. The two stages are in serial for most of the methods. This simple combination has not achieved superiority of fusing local and global descriptors. The 3D points obtained from the retrieval feedback are as the nearest neighbor candidates of the 2D image points only by global descriptors. Each of the 2D image points is also called a query local feature when performing the 2D-3D point correspondences. In this paper, we propose a novel parallel search framework, which leverages advantages of both local and global descriptors to get nearest neighbor candidates of a query local feature. Specifically, besides using deep learning based global descriptors, we also utilize local descriptors to construct random tree structures for obtaining nearest neighbor candidates of the query local feature. We propose a new probabilistic model and a new deep learning based local descriptor when constructing the random trees. A weighted Hamming regularization term to keep discriminativeness after binarization is given in the loss function for the proposed local descriptor. The loss function co-trains both real and binary descriptors of which the results are integrated into the random trees.
Co-salient object detection (CoSOD) has recently achieved significant progress and played a key role in retrieval-related tasks. However, it inevitably poses an entirely new safety and security issue, i.e., highly personal and sensitive content can potentially be extracting by powerful CoSOD methods. In this paper, we address this problem from the perspective of adversarial attacks and identify a novel task: adversarial co-saliency attack. Specially, given an image selected from a group of images containing some common and salient objects, we aim to generate an adversarial version that can mislead CoSOD methods to predict incorrect co-salient regions. Note that, compared with general white-box adversarial attacks for classification, this new task faces two additional challenges: (1) low success rate due to the diverse appearance of images in the group; (2) low transferability across CoSOD methods due to the considerable difference between CoSOD pipelines. To address these challenges, we propose the very first black-box joint adversarial exposure and noise attack (Jadena), where we jointly and locally tune the exposure and additive perturbations of the image according to a newly designed high-feature-level contrast-sensitive loss function. Our method, without any information on the state-of-the-art CoSOD methods, leads to significant performance degradation on various co-saliency detection datasets and makes the co-salient objects undetectable. This can have strong practical benefits in properly securing the large number of personal photos currently shared on the Internet. Moreover, our method is potential to be utilized as a metric for evaluating the robustness of CoSOD methods.
Visual place recognition is the task of recognizing a place depicted in an image based on its pure visual appearance without metadata. In visual place recognition, the challenges lie upon not only the changes in lighting conditions, camera viewpoint, and scale but also the characteristic of scene-level images and the distinct features of the area. To resolve these challenges, one must consider both the local discriminativeness and the global semantic context of images. On the other hand, the diversity of the datasets is also particularly important to develop more general models and advance the progress of the field. In this paper, we present a fully-automated system for place recognition at a city-scale based on content-based image retrieval. Our main contributions to the community lie in three aspects. Firstly, we take a comprehensive analysis of visual place recognition and sketch out the unique challenges of the task compared to general image retrieval tasks. Next, we propose yet a simple pooling approach on top of convolutional neural network activations to embed the spatial information into the image representation vector. Finally, we introduce new datasets for place recognition, which are particularly essential for application-based research. Furthermore, throughout extensive experiments, various issues in both image retrieval and place recognition are analyzed and discussed to give some insights into improving the performance of retrieval models in reality. The dataset used in this paper can be found at https://github.com/canhld94/Daejeon520
Scene text instances found in natural images carry explicit semantic information that can provide important cues to solve a wide array of computer vision problems. In this paper, we focus on leveraging multi-modal content in the form of visual and textual cues to tackle the task of fine-grained image classification and retrieval. First, we obtain the text instances from images by employing a text reading system. Then, we combine textual features with salient image regions to exploit the complementary information carried by the two sources. Specifically, we employ a Graph Convolutional Network to perform multi-modal reasoning and obtain relationship-enhanced features by learning a common semantic space between salient objects and text found in an image. By obtaining an enhanced set of visual and textual features, the proposed model greatly outperforms the previous state-of-the-art in two different tasks, fine-grained classification and image retrieval in the Con-Text and Drink Bottle datasets.
Conventional image retrieval techniques for Structure-from-Motion (SfM) suffer from the limit of effectively recognizing repetitive patterns and cannot guarantee to create just enough match pairs with high precision and high recall. In this paper, we present a novel retrieval method based on Graph Convolutional Network (GCN) to generate accurate pairwise matches without costly redundancy. We formulate image retrieval task as a node binary classification problem in graph data: a node is marked as positive if it shares the scene overlaps with the query image. The key idea is that we find that the local context in feature space around a query image contains rich information about the matchable relation between this image and its neighbors. By constructing a subgraph surrounding the query image as input data, we adopt a learnable GCN to exploit whether nodes in the subgraph have overlapping regions with the query photograph. Experiments demonstrate that our method performs remarkably well on the challenging dataset of highly ambiguous and duplicated scenes. Besides, compared with state-of-the-art matchable retrieval methods, the proposed approach significantly reduces useless attempted matches without sacrificing the accuracy and completeness of reconstruction.
With the rapid development of social websites, recent years have witnessed an explosive growth of social images with user-provided tags which continuously arrive in a streaming fashion. Due to the fast query speed and low storage cost, hashing-based methods for image search have attracted increasing attention. However, existing hashing methods for social image retrieval are based on batch mode which violates the nature of social images, i.e., social images are usually generated periodically or collected in a stream fashion. Although there exist many online image hashing methods, they either adopt unsupervised learning which ignore the relevant tags, or are designed in the supervised manner which needs high-quality labels. In this paper, to overcome the above limitations, we propose a new method named Weakly-supervised Online Hashing (WOH). In order to learn high-quality hash codes, WOH exploits the weak supervision by considering the semantics of tags and removing the noise. Besides, We develop a discrete online optimization algorithm for WOH, which is efficient and scalable. Extensive experiments conducted on two real-world datasets demonstrate the superiority of WOH compared with several state-of-the-art hashing baselines.
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 activation mapping loss (Grad-SAM) is incorporated for finer localization with high accuracy. We also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised manner. The final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models without and with Grad-SAM loss. Extensive experiments have been conducted to validate the effectiveness of the proposed approach on the CMUSeasons dataset. The strong generalization ability of our approach is verified on RobotCar dataset using models pre-trained on urban part of CMU-Seasons dataset. Our performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision, especially under the challenging environments with illumination variance, vegetation and night-time images. The code and pretrained models are available on https://github.com/HanjiangHu/DISAM.
The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to navigate visual search can help tailor retrieved results to specific user queries. We focus on the task of text-conditioned image retrieval that utilizes support text feedback alongside a reference image to retrieve images that concurrently satisfy constraints imposed by both inputs. The task is challenging since it requires learning composite image-text features by incorporating multiple cross-granular semantic edits from text feedback and then applying the same to visual features. To address this, we propose a novel framework SAC which resolves the above in two major steps: "where to see" (Semantic Feature Attention) and "how to change" (Semantic Feature Modification). We systematically show how our architecture streamlines the generation of text-aware image features by removing the need for various modules required by other state-of-art techniques. We present extensive quantitative, qualitative analysis, and ablation studies, to show that our architecture SAC outperforms existing techniques by achieving state-of-the-art performance on 3 benchmark datasets: FashionIQ, Shoes, and Birds-to-Words, while supporting natural language feedback of varying lengths.
The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly. However, in many real-world searching scenarios (e.g., video surveillance), the objects (e.g., persons, vehicles, etc.) are seldom accurately detected or annotated. Therefore, object-level retrieval becomes intractable without bounding-box annotation, which leads to a new but challenging topic, i.e. image-level search. In this paper, to address the image search issue, we first introduce an end-to-end Integrated Net (I-Net), which has three merits: 1) A Siamese architecture and an on-line pairing strategy for similar and dissimilar objects in the given images are designed. 2) A novel on-line pairing (OLP) loss is introduced with a dynamic feature dictionary, which alleviates the multi-task training stagnation problem, by automatically generating a number of negative pairs to restrict the positives. 3) A hard example priority (HEP) based softmax loss is proposed to improve the robustness of classification task by selecting hard categories. With the philosophy of divide and conquer, we further propose an improved I-Net, called DC-I-Net, which makes two new contributions: 1) two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed. 2) A class-center guided HEP loss (C2HEP) by exploiting the stored class centers is proposed, such that the intra-similarity and inter-dissimilarity can be captured for ultimate retrieval. Extensive experiments on famous image-level search oriented benchmark datasets demonstrate that the proposed DC-I-Net outperforms the state-of-the-art tasks-integrated and tasks-separated image search models.
The rise of deep learning applications in the fashion industry has fueled advances in curating large-scale datasets to build applications for product design, image retrieval, and recommender systems. In this paper, the author proposes using Variational Autoencoder (VAE) to build an interactive fashion product application framework that allows the users to generate products with attributes according to their liking, retrieve similar styles for the same product category, and receive content-based recommendations from other categories. Fashion product images dataset containing eyewear, footwear, and bags are appropriate to illustrate that this pipeline is applicable in the booming industry of e-commerce enabling direct user interaction in specifying desired products paired with new methods for data matching, and recommendation systems by using VAE and exploiting its generated latent codes.
Many practical applications, e.g., content based image retrieval and object recognition, heavily rely on the local features extracted from the query image. As these local features are usually exposed to untrustworthy parties, the privacy leakage problem of image local features has received increasing attention in recent years. In this work, we thoroughly evaluate the privacy leakage of Scale Invariant Feature Transform (SIFT), which is one of the most widely-used image local features. We first consider the case that the adversary can fully access the SIFT features, i.e., both the SIFT descriptors and the coordinates are available. We propose a novel end-to-end, coarse-to-fine deep generative model for reconstructing the latent image from its SIFT features. The designed deep generative model consists of two networks, where the first one attempts to learn the structural information of the latent image by transforming from SIFT features to Local Binary Pattern (LBP) features, while the second one aims to reconstruct the pixel values guided by the learned LBP. Compared with the state-of-the-art algorithms, the proposed deep generative model produces much improved reconstructed results over three public datasets. Furthermore, we address more challenging cases that only partial SIFT features (either SIFT descriptors or coordinates) are accessible to the adversary. It is shown that, if the adversary can only have access to the SIFT descriptors while not their coordinates, then the modest success of reconstructing the latent image can be achieved for highly-structured images (e.g., faces) and would fail in general settings. In addition, the latent image can be reconstructed with reasonably good quality solely from the SIFT coordinates. Our results would suggest that the privacy leakage problem can be largely avoided if the SIFT coordinates can be well protected.
Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification. The existing approaches for person, vehicle, or animal re-identification tasks suffer from high intra-class variance due to deformable shapes and different camera viewpoints. To overcome this limitation, we propose to align the image embedding with a predefined order of the keypoints. The proposed keypoint aligned embeddings model (KAE-Net) learns part-level features via multi-task learning which is guided by keypoint locations. More specifically, KAE-Net extracts channels from a feature map activated by a specific keypoint through learning the auxiliary task of heatmap reconstruction for this keypoint. The KAE-Net is compact, generic and conceptually simple. It achieves state of the art performance on the benchmark datasets of CUB-200-2011, Cars196 and VeRi-776 for retrieval and re-identification tasks.
Image retrieval is a fundamental problem in computer vision. This paper presents our 3rd place detailed solution to the Google Landmark Retrieval 2020 challenge. We focus on the exploration of data cleaning and models with metric learning. We use a data cleaning strategy based on embedding clustering. Besides, we employ a data augmentation method called Corner-Cutmix, which improves the model's ability to recognize multi-scale and occluded landmark images. We show in detail the ablation experiments and results of our method.
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like in person re-identification or image retrieval. Our learning scheme exploits the idea of leveraging information from labeled to unlabeled data. Instead of fitting the associated class-wise similarity scores as most meta-learning algorithms do, we propose to derive semantics-oriented similarity representations from labeled data, and transfer such representation to unlabeled ones. Thus, our strategy can be viewed as a self-supervised learning scheme, which can be applied to fully supervised learning tasks for improved performance. Our experiments on various tasks and settings confirm the effectiveness of our proposed approach and its superiority over the state-of-the-art methods.