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.
In this paper, we explore how three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework, which is trained without the need of training data with point to point correspondences. By leveraging diverse information from sequential layers of a standard ResNet-based architecture, we are able to extract keypoints and descriptors that encode local information using generic techniques such as local activation norms, channel grouping and dropping, and self-distillation. Subsequently, global information for image retrieval is …
Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of the detection-description pipeline to describe local image structures. Recently, some, or all, of these stages have been replaced by convolutional neural networks (CNNs), in order to increase their performance. A detector is defined as a selection problem, which makes it more challenging to implement as a CNN. They are therefore generally defined as regressors, converting input i…
University of Social Sciences in Łódź（罗兹社会科学大学）；University of Geneva（日内瓦大学）
This paper describes a method for searching for common sets of descriptors between collections of images. The presented method operates on local interest keypoints, which are generated using the SURF algorithm. The use of a dictionary of descriptors allowed achieving good performance of the content-based image retrieval. The method can be used to initially determine a set of similar pairs of keypoints between images. For this purpose, we use a certain level of tolerance between values of descriptors, as values of feature descriptors are almost never equal but similar between different images. …
We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred to as DELF (DEep Local Feature). The new feature is based on convolutional neural networks, which are trained only with image-level annotations on a landmark image dataset. To identify semantically useful local features for image retrieval, we also propose an attention mechanism for keypoint selection, which shares most network layers with the descriptor. This framework can be used for image retrieval as a drop-in replacement for other keypoint detectors and descriptors, enabling more accurate f…
A novel efficient method for content-based image retrieval (CBIR) is developed in this paper using both texture and color features. Our motivation is to represent and characterize an input image by a set of local descriptors extracted at characteristic points (i.e. keypoints) within the image. Then, dissimilarity measure between images is calculated based on the geometric distance between the topological feature spaces (i.e. manifolds) formed by the sets of local descriptors generated from these images. In this work, we propose to extract and use the local extrema pixels as our feature points.…
In many mobile visual analysis applications, compressed video is transmitted over a communication network and analyzed by a server. Typical processing steps performed at the server include keypoint detection, descriptor calculation, and feature matching. Video compression has been shown to have an adverse effect on feature-matching performance. The negative impact of compression can be reduced by using the keypoints extracted from the uncompressed video to calculate descriptors from the compressed video. Based on this observation, we propose to provide these keypoints to the server as side inf…
Tsinghua University（清华大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of a keypoint are employed. However, such strategy does not consider the contextual evidences of a keypoint, a problem which would lead to the prevalence of false matches. To address this problem, this paper defines "true match" as a pair of keypoints which are similar on three levels, i.e., local, regional, and global. Then, a principled probabilistic framework is established, which is capable of implicitly integratin…
George Mason University（乔治梅森大学）；Siemens Corporate Technology（西门子企业技术部）
Finding correspondences between images or 3D scans is at the heart of many computer vision and image retrieval applications and is often enabled by matching local keypoint descriptors. Various learning approaches have been applied in the past to different stages of the matching pipeline, considering detector, descriptor, or metric learning objectives. These objectives were typically addressed separately and most previous work has focused on image data. This paper proposes an end-to-end learning framework for keypoint detection and its representation (descriptor) for 3D depth maps or 3D scans, …
University of Science and Technology Beijing（北京科技大学）
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a challenging cross-modal retrieval task. In prior arts, the retrieval is conducted by sorting the distance between the query sketch and each image in the gallery. However, the domain gap and the zero-shot setting make neural networks hard to generalize. This paper tackles the challenges from a new perspective: utilizing gallery image features. We propose a Cluster-then-Retrieve (ClusterRetri) method that performs clustering on the gallery images and uses the cluster centroids as proxies for retrieval. Furthermore, a distribution alignment lo…
Shanghai Jiao Tong University（上海交通大学）；East China Normal University（华东师范大学）
Point cloud completion aims at completing geometric and topological shapes from a partial observation. However, some topology of the original shape is missing, existing methods directly predict the location of complete points, without predicting structured and topological information of the complete shape, which leads to inferior performance. To better tackle the missing topology part, we propose LAKe-Net, a novel topology-aware point cloud completion model by localizing aligned keypoints, with a novel Keypoints-Skeleton-Shape prediction manner. Specifically, our method completes missing topol…
Shanghai Jiao Tong University（上海交通大学）；Qing Yuan Research Institute（清源研究院）
Detecting aligned 3D keypoints is essential under many scenarios such as object tracking, shape retrieval and robotics. However, it is generally hard to prepare a high-quality dataset for all types of objects due to the ambiguity of keypoint itself. Meanwhile, current unsupervised detectors are unable to generate aligned keypoints with good coverage. In this paper, we propose an unsupervised aligned keypoint detector, Skeleton Merger, which utilizes skeletons to reconstruct objects. It is based on an Autoencoder architecture. The encoder proposes keypoints and predicts activation strengths of …
Jilian Technology Group（极链科技集团）；Video++ AI Lab（Video++人工智能实验室）
It has been shown that image descriptors extracted by convolutional neural networks (CNNs) achieve remarkable results for retrieval problems. In this paper, we apply attention mechanism to CNN, which aims at enhancing more relevant features that correspond to important keypoints in the input image. The generated attention-aware features are then aggregated by the previous state-of-the-art generalized mean (GeM) pooling followed by normalization to produce a compact global descriptor, which can be efficiently compared to other image descriptors by the dot product. An extensive comparison of our…
Purdue University（普渡大学）；University of Florida（佛罗里达大学）；Fudan University（复旦大学）
In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more keypoint features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. We use a weakly supervised triplet ranking loss to learn discriminat…
In computer vision, finding point correspondence among images plays an important role in many applications, such as image stitching, image retrieval, visual localization, etc. Most of the research worksfocus on the matching of local feature before a sampling method is employed, such as RANSAC, to verify initial matching results via repeated fitting of certain global transformation among the images. However, incorrect matches may still exist, while careful examination of such problems is often skipped. Accordingly, a geometrically constrained algorithm is proposed in this work to verify the cor…
National Textile University（国立纺织大学）；University of Engineering & Technology, Taxila（塔克西拉工程技术大学）
One of the challenges in Content-Based Image Retrieval (CBIR) is to reduce the semantic gaps between low-level features and high-level semantic concepts. In CBIR, the images are represented in the feature space and the performance of CBIR depends on the type of selected feature representation. Late fusion also known as visual words integration is applied to enhance the performance of image retrieval. The recent advances in image retrieval diverted the focus of research towards the use of binary descriptors as they are reported computationally efficient. In this paper, we aim to investigate the…
Computer Vision Center（计算机视觉中心）；Autonomous University of Barcelona（巴塞罗那自治大学）；Amsterdam Machine Learning Lab（阿姆斯特丹机器学习实验室）；University of Amsterdam（阿姆斯特丹大学）
Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase. Existing works either require aligned sketch-image pairs or inefficient memory fusion layer for mapping the visual information to a semantic space. In this work, we propose a semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maps the visual information to a common semantic space via an adversarial training. Each of these branches maintains …
University of Zagreb, Faculty of Electrical Engineering and Computing（萨格勒布大学电气工程与计算学院）；Linköping University（林雪平大学）
Current best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs. However, data of this kind is not always available since detailed keypoint correspondences can be hard to establish. On the other hand, we can often obtain labels for pairs of keypoint bags. For example, keypoint bags extracted from two images of the same object under different views form a matching pair, and keypoint bags extracted from images of different objects form a non-matching pair. On average, matching pairs should contain more corresponding keypoints than non-matching pairs. We …
Learning What Helps: Task-Aligned Context Selection for Vision Tasks
KTH Royal Institute of Technology（皇家理工学院）；Science for Life Laboratory（生命科学实验室）；Karolinska Institutet（卡罗林斯卡研究院）；Pathology, Clinical Pharmacology and Safety Sciences, R&D AstraZeneca（病理学、临床药理学与安全性科学，阿斯利康研发部）
Learning-based Relational Object Matching Across Views
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck ETH Center for Learning Systems（马克斯·普朗克-苏黎世联邦理工学院学习系统中心）；ETH Zurich（苏黎世联邦理工学院）；University of Amsterdam（阿姆斯特丹大学）；Microsoft Mixed Reality and AI Lab（微软混合现实与人工智能实验室）
University of Notre Dame（圣母大学）；University of Campinas（坎皮纳斯大学）
Images from social media can reflect diverse viewpoints, heated arguments, and expressions of creativity, adding new complexity to retrieval tasks. Researchers working onContent-Based Image Retrieval (CBIR) have traditionally tuned their algorithms to match filtered results with user search intent. However, we are now bombarded with composite images of unknown origin, authenticity, and even meaning. With such uncertainty, users may not have an initial idea of what the results of a search query should look like. For instance, hidden people, spliced objects, and subtly altered scenes can be diff…
Stanford University（斯坦福大学）；Google Research（谷歌研究院）；Massachusetts Institute of Technology（麻省理工学院）；Facebook AI Research（Facebook人工智能研究院）
Understanding 3D object structure from a single image is an important but difficult task in computer vision, mostly due to the lack of 3D object annotations in real images. Previous work tackles this problem by either solving an optimization task given 2D keypoint positions, or training on synthetic data with ground truth 3D information. In this work, we propose 3D INterpreter Network (3D-INN), an end-to-end framework which sequentially estimates 2D keypoint heatmaps and 3D object structure, trained on both real 2D-annotated images and synthetic 3D data. This is made possible mainly by two tec…
VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale
Institute of Artificial Intelligence, University of Central Florida（人工智能研究所，中央佛罗里达大学）；Luleå Tekniska Universitet（卢勒奥理工大学）；Amazon Prime Video Science（亚马逊Prime视频科学）
The goal of this paper is to retrieve an image based on instance, attribute and category similarity notions. Different from existing works, which usually address only one of these entities in isolation, we introduce a cooperative embedding to integrate them while preserving their specific level of semantic representation. An algebraic structure defines a superspace filled with instances. Attributes are axis-aligned to form subspaces, while categories influence the arrangement of similar instances. These relationships enable them to cooperate for their mutual benefits for image retrieval. We de…
University of Exeter（埃克塞特大学）；University of Tübingen（图宾根大学）
Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase. Related prior works either require aligned sketch-image pairs that are costly to obtain or inefficient memory fusion layer for mapping the visual information to a semantic space. In this paper, we address any-shot, i.e. zero-shot and few-shot, sketch-based image retrieval (SBIR) tasks, where we introduce the few-shot setting for SBIR. For solving these tasks, we propose a semantically aligned pair…
PointT2I: LLM-based text-to-image generation via keypoints
Interdisciplinary Program in Artificial Intelligence, Seoul National University（人工智能跨学科项目，首尔国立大学）；Department of Mathematical Sciences, Seoul National University（数学科学系，首尔国立大学）
An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye. This paper presents an analysis of adversarial queries for CBIR based on neural, local, and global features. We introduce an innovative neural image perturbation approach, called Perturbations for Image Retrieval Error (PIRE), that is capable of blocking neural-feature-based CBIR. PIRE differs significantly from existing approaches that create images adversarial with respect to CNN classifiers because it is unsupervised, i.e., it needs no la…
Massachusetts Institute of Technology（麻省理工学院）；Google Research（谷歌研究院）；University of Southern California（南加州大学）；Facebook Inc.（脸书公司）
Understanding 3D object structure from a single image is an important but challenging task in computer vision, mostly due to the lack of 3D object annotations to real images. Previous research tackled this problem by either searching for a 3D shape that best explains 2D annotations, or training purely on synthetic data with ground truth 3D information. In this work, we propose 3D INterpreter Networks (3D-INN), an end-to-end trainable framework that sequentially estimates 2D keypoint heatmaps and 3D object skeletons and poses. Our system learns from both 2D-annotated real images and synthetic 3…
In this paper, we propose a method for keypoint discovery from a 2D image using image-level supervision. Recent works on unsupervised keypoint discovery reliably discover keypoints of aligned instances. However, when the target instances have high viewpoint or appearance variation, the discovered keypoints do not match the semantic correspondences over different images. Our work aims to discover keypoints even when the target instances have high viewpoint and appearance variation by using image-level supervision. Motivated by the weakly-supervised learning approach, our method exploits image-l…
We tackle the cross-modal retrieval problem, where learning is only supervised by relevant multi-modal pairs in the data. Although the contrastive learning is the most popular approach for this task, it makes potentially wrong assumption that the instances in different pairs are automatically irrelevant. To address the issue, we propose a novel loss function that is based on self-labeling of the unknown semantic classes. Specifically, we aim to predict class labels of the data instances in each modality, and assign those labels to the corresponding instances in the other modality (i.e., swappi…
Enhancing Deformable Local Features by Jointly Learning to Detect and Describe Keypoints
Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）；Google Research（谷歌研究院）；Université de Bourgogne（勃艮第大学）；Université de Lorraine（洛林大学）；Inria（法国国家信息与自动化研究所）；Microsoft（微软）
ETH Zürich（苏黎世联邦理工学院）；Reality Labs Research（现实实验室研究部门）；Meta
Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geometric consistency to reduce spatial ambiguity. However, global encodings often suffer from overfitting to the distribution of the training data, and it is difficult to learn multi-view consistent reconstruction from sparse views. In this work, we investigate common issues with existing spatial encodings and propose a simple yet highly effective approach to modeling high-fidelity volumetric humans from sparse views. On…
Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）；Université Bourgogne Franche-Comté（勃艮第-弗朗什-孔泰大学）
We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence. Our training framework uses true correspondences, obtained by matching annotated image pairs with a predefined descriptor extractor, as a ground-truth to train a convolutional neural network (CNN). We optimize the model architecture by applying known geometric transformations to images as the supervisory signal. Experiments show that our method outperforms the state-of-the-art keypoint detector on real images of non-rigid objects by 20 p.p. on …
In ophthalmological imaging, multiple imaging systems, such as color fundus, infrared, fluorescein angiography, optical coherence tomography (OCT) or OCT angiography, are often involved to make a diagnosis of retinal disease. Multi-modal retinal registration techniques can assist ophthalmologists by providing a pixel-based comparison of aligned vessel structures in images from different modalities or acquisition times. To this end, we propose an end-to-end trainable deep learning method for multi-modal retinal image registration. Our method extracts convolutional features from the vessel struc…
Image retrieval relies heavily on the quality of the data modeling and the distance measurement in the feature space. Building on the concept of image manifold, we first propose to represent the feature space of images, learned via neural networks, as a graph. Neighborhoods in the feature space are now defined by the geodesic distance between images, represented as graph vertices or manifold samples. When limited images are available, this manifold is sparsely sampled, making the geodesic computation and the corresponding retrieval harder. To address this, we augment the manifold samples with …
Unsupervised Keypoints from Pretrained Diffusion Models
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（向量人工智能研究所）；Google Research（谷歌研究院）；Google DeepMind（谷歌DeepMind）；Simon Fraser University（西蒙菲莎大学）；University of Toronto（多伦多大学）
KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model
Sun Yat-sen University, Shenzhen（中山大学深圳校区）；Chinese University of Hong Kong, Shenzhen（香港中文大学深圳校区）；SenseTime Research（商汤科技研究院）；Chinese University of Hong Kong（香港中文大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）
The retrieval of the 3D pose and shape of objects from images is an ill-posed problem. A common way to object reconstruction is to match entities such as keypoints, edges, or contours of a deformable 3D model, used as shape prior, to their corresponding entities inferred from the image. However, such approaches are highly sensitive to model initialisation, imprecise keypoint localisations and/or illumination conditions. In this paper, we present a probabilistic approach for shape-aware 3D vehicle reconstruction from stereo images that leverages the outputs of a novel multi-task CNN. Specifical…
National Institute of Standards and Technology（美国国家标准与技术研究院）；QUEST University（奎斯特大学）
In this paper we describe a new formulation for the 3D salient local features based on the voxel grid inspired by the Scale Invariant Feature Transform (SIFT). We use it to identify the salient keypoints (invariant points) on a 3D voxelized model and calculate invariant 3D local feature descriptors at these keypoints. We then use the bag of words approach on the 3D local features to represent the 3D models for shape retrieval. The advantages of the method are that it can be applied to rigid as well as to articulated and deformable 3D models. Finally, this approach is applied for 3D Shape Retri…
This paper presents an efficient method for texture retrieval using multiscale feature extraction and embedding based on the local extrema keypoints. The idea is to first represent each texture image by its local maximum and local minimum pixels. The image is then divided into regular overlapping blocks and each one is characterized by a feature vector constructed from the radiometric, geometric and structural information of its local extrema. All feature vectors are finally embedded into a covariance matrix which will be exploited for dissimilarity measurement within retrieval task. Thanks to…
École Polytechnique de Montréal（蒙特利尔高等理工学院）；École de technologie supérieure（高等工程技术学院）
In this paper, an automatic method is proposed to perform image registration in visible and infrared pair of video sequences for multiple targets. In multimodal image analysis like image fusion systems, color and IR sensors are placed close to each other and capture a same scene simultaneously, but the videos are not properly aligned by default because of different fields of view, image capturing information, working principle and other camera specifications. Because the scenes are usually not planar, alignment needs to be performed continuously by extracting relevant common information. In th…
Nanyang Technological University（南洋理工大学）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection. However, DETR suffers from slow training convergence, which hinders its applicability to various detection tasks. We observe that DETR's slow convergence is largely attributed to the difficulty in matching object queries to relevant regions due to the unaligned semantics between object queries and encoded image features. With this observation, we design Semantic-Aligned-Matching DETR++ (SAM-DETR++) to accelerate DETR's convergence and improve detection performance. The core of S…
To increase the computational efficiency of interest-point based object retrieval, researchers have put remarkable research efforts into improving the efficiency of kNN-based feature matching, pursuing to match thousands of features against a database within fractions of a second. However, due to the high-dimensional nature of image features that reduces the effectivity of index structures (curse of dimensionality), due to the vast amount of features stored in image databases (images are often represented by up to several thousand features), this ultimate goal demanded to trade query runtimes …
