Image and video descriptors are an omnipresent tool in computer vision and its application fields like mobile robotics. Many hand-crafted and in particular learned image descriptors are numerical vectors with a potentially (very) large number of dimensions. Practical considerations like memory consumption or time for comparisons call for the creation of compact representations. In this paper, we use hyperdimensional computing (HDC) as an approach to systematically combine information from a set of vectors in a single vector of the same dimensionality. HDC is a known technique to perform symbolic processing with distributed representation in numerical vectors with thousands of dimensions. We present a HDC implementation that is suitable for processing the output of existing and future (deep-learning based) image descriptors. We discuss how this can be used as a framework to process descriptors together with additional knowledge by simple and fast vector operations. A concrete outcome is a novel HDC-based approach to aggregate a set of local image descriptors together with their image positions in a single holistic descriptor. The comparison to available holistic descriptors and aggregation methods on a series of standard mobile robotics place recognition experiments shows a 20% improvement in average performance compared to runner-up and 3.6x better worst-case performance.
Queensland University of Technology（昆士兰科技大学）；University of Adelaide（阿德莱德大学）
We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection. In contrast to most existing work that performs OOD detection based on only a single layer of a neural network, we use similarity-preserving semi-orthogonal projection matrices to project the feature maps from multiple layers into a common vector space. By repeatedly applying the bundling operation $\oplus$, we create expressive class-specific descriptor vectors for all in-distribution classes. At test time, a simple and efficient cosine similarity calculation between …
QUT Centre for Robotics（昆士兰科技大学机器人中心）；School of Electrical Engineering and Robotics, QUT（昆士兰科技大学电气工程与机器人学院）；Queensland University of Technology (QUT)（昆士兰科技大学）
Visual Place Recognition (VPR) is the task of matching current visual imagery from a camera to images stored in a reference map of the environment. While initial VPR systems used simple direct image methods or hand-crafted visual features, recent work has focused on learning more powerful visual features and further improving performance through either some form of sequential matcher / filter or a hierarchical matching process. In both cases the performance of the initial single-image based system is still far from perfect, putting significant pressure on the sequence matching or (in the case …
Image search systems based on local descriptors typically achieve orientation invariance by aligning the patches on their dominant orientations. Albeit successful, this choice introduces too much invariance because it does not guarantee that the patches are rotated consistently. This paper introduces an aggregation strategy of local descriptors that achieves this covariance property by jointly encoding the angle in the aggregation stage in a continuous manner. It is combined with an efficient monomial embedding to provide a codebook-free method to aggregate local descriptors into a single vect…
In this paper we present an efficient method for aggregating binary feature descriptors to allow compact representation of 3D scene model in incremental structure-from-motion and SLAM applications. All feature descriptors linked with one 3D scene point or landmark are represented by a single low-dimensional real-valued vector called a \emph{prototype}. The method allows significant reduction of memory required to store and process feature descriptors in large-scale structure-from-motion applications. An efficient approximate nearest neighbours search methods suited for real-valued descriptors,…
Given a set of hand-crafted local features, acquiring a global representation via aggregation is a promising technique to boost computational efficiency and improve task performance. Existing feature aggregation (FA) approaches, including Bag of Words and Fisher Vectors, usually fail to capture the desired information due to their pipeline mode. In this paper, we propose a generic formulation to provide a systematical solution (named ProLFA) to aggregate local descriptors. It is capable of producing compact yet interpretable representations by selecting representative prototypes from numerous …
Deep convolutional neural network models pre-trained for the ImageNet classification task have been successfully adopted to tasks in other domains, such as texture description and object proposal generation, but these tasks require annotations for images in the new domain. In this paper, we focus on a novel and challenging task in the pure unsupervised setting: fine-grained image retrieval. Even with image labels, fine-grained images are difficult to classify, let alone the unsupervised retrieval task. We propose the Selective Convolutional Descriptor Aggregation (SCDA) method. SCDA firstly lo…
The objective of this work is to learn a compact embedding of a set of descriptors that is suitable for efficient retrieval and ranking, whilst maintaining discriminability of the individual descriptors. We focus on a specific example of this general problem -- that of retrieving images containing multiple faces from a large scale dataset of images. Here the set consists of the face descriptors in each image, and given a query for multiple identities, the goal is then to retrieve, in order, images which contain all the identities, all but one, \etc To this end, we make the following contributi…
This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. The feature extractors extract dense features from the ground and aerial images. Given a set of candidate camera poses, the feature aggregators construct a single ground descriptor and a set of pose-dependent aerial descriptors. Notably, our novel aerial feature aggregator has a cross-view atten…
Korea University（高丽大学）；Microsoft Research Asia（微软亚洲研究院）
We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation. However, they generally aggregate one or the other but not both, though joint aggregation would boost each other by providing information that one has but other lacks, i.e., structural or semantic information of an image, or pixel-wise matching similarity. In this work, we propose a novel Transformer-based network that interleaves both forms of aggregations in a way that exploits their complementary informat…
Institute of Information Science and Technologies (ISTI) - CNR（意大利国家研究委员会信息科学与技术研究所 (ISTI)）
Content-Based Image Retrieval based on local features is computationally expensive because of the complexity of both extraction and matching of local feature. On one hand, the cost for extracting, representing, and comparing local visual descriptors has been dramatically reduced by recently proposed binary local features. On the other hand, aggregation techniques provide a meaningful summarization of all the extracted feature of an image into a single descriptor, allowing us to speed up and scale up the image search. Only a few works have recently mixed together these two research directions, …
RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation
Australian Institute for Machine Learning (AIML)（澳大利亚机器学习研究所）；The University of Adelaide（阿德莱德大学）；Queensland University of Technology（昆士兰科技大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Yandex（扬德克斯）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
Several recent works have shown that image descriptors produced by deep convolutional neural networks provide state-of-the-art performance for image classification and retrieval problems. It has also been shown that the activations from the convolutional layers can be interpreted as local features describing particular image regions. These local features can be aggregated using aggregation approaches developed for local features (e.g. Fisher vectors), thus providing new powerful global descriptors. In this paper we investigate possible ways to aggregate local deep features to produce compact g…
Das-nano；Veridas；Universidad Pública de Navarra（纳瓦拉公立大学）
Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor for a given region (local or global). The resultant combined vector must be as discriminant as possible, in other words, must contain relevant information, while removing irrelevant and confusing details. Maximum and average are the most common aggregation functions used in the pooling step. To improve the aggregation of relevant information without degrading their discrimi…
Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Pengcheng Laboratory（鹏城实验室）；Shenyang Institute of Automation, Chinese Academy of Sciences（沈阳自动化研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））
The recent advances brought by deep learning allowed to improve the performance in image retrieval tasks. Through the many convolutional layers, available in a Convolutional Neural Network (CNN), it is possible to obtain a hierarchy of features from the evaluated image. At every step, the patches extracted are smaller than the previous levels and more representative. Following this idea, this paper introduces a new detector applied on the feature maps extracted from pre-trained CNN. Specifically, this approach lets to increase the number of features in order to increase the performance of the …
Auditing Training-Free 3D Shape Retrieval with Diffused Geodesic Moments
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Guangzhou International Economics College（广州国际经济学院）；School of Electrical and Electronic Engineering, The University of Sheffield（谢菲尔德大学电子与电气工程学院）
This paper addresses the problem of very large-scale image retrieval, focusing on improving its accuracy and robustness. We target enhanced robustness of search to factors such as variations in illumination, object appearance and scale, partial occlusions, and cluttered backgrounds - particularly important when search is performed across very large datasets with significant variability. We propose a novel CNN-based global descriptor, called REMAP, which learns and aggregates a hierarchy of deep features from multiple CNN layers, and is trained end-to-end with a triplet loss. REMAP explicitly l…
Xerox Research Centre Europe（施乐欧洲研究中心）；Facebook AI Research（Facebook人工智能研究院）；University of Oxford（牛津大学）
We consider the design of an image representation that embeds and aggregates a set of local descriptors into a single vector. Popular representations of this kind include the bag-of-visual-words, the Fisher vector and the VLAD. When two such image representations are compared with the dot-product, the image-to-image similarity can be interpreted as a match kernel. In match kernels, one has to deal with interference, i.e. with the fact that even if two descriptors are unrelated, their matching score may contribute to the overall similarity. We formalise this problem and propose two related solu…
We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets. Our key innovation is a learnable activation layer designed to improve the signal-to-noise ratio (SNR) of deep convolutional feature maps. Further, we introduce a controlled multi-stream aggregation, where complementary deep features from different convolutional layers are optimally transformed and balanced using our novel activation layers, before aggregation into a global descriptor. Importantly, the learnable parameters of our activation blocks are explicitly trained, together wi…
ETIS UMR 8051, Université Paris Seine, UCP, ENSEA, CNRS（ETIS UMR 8051，巴黎塞纳大学，塞尔吉-蓬图瓦兹大学，国立高等电子及应用工程师学院，法国国家科学研究中心）；Sorbonne Universités, Laboratoire d’Informatique de Paris 6, LIP6（索邦大学，巴黎第六大学计算机实验室（LIP6））；C3N, Pôle Judiciaire de la Gendarmerie Nationale（C3N，法国国家宪兵队司法中心）
Most image retrieval methods use global features that aggregate local distinctive patterns into a single representation. However, the aggregation process destroys the relative spatial information by considering orderless sets of local descriptors. We propose to integrate relative spatial information into the aggregation process by taking into account co-occurrences of local patterns in a tensor framework. The resulting signature called Improved Spatial Tensor Aggregation (ISTA) is able to reach state of the art performances on well known datasets such as Holidays, Oxford5k and Paris6k.
One of the key challenges of deep learning based image retrieval remains in aggregating convolutional activations into one highly representative feature vector. Ideally, this descriptor should encode semantic, spatial and low level information. Even though off-the-shelf pre-trained neural networks can already produce good representations in combination with aggregation methods, appropriate fine tuning for the task of image retrieval has shown to significantly boost retrieval performance. In this paper, we present a simple yet effective supervised aggregation method built on top of existing reg…
Efficient Match Pair Retrieval for Large-scale UAV Images via Graph Indexed Global Descriptor
China University of Geosciences（中国地质大学）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)（广东省人工智能与数字经济实验室（深圳））；Shenzhen University（深圳大学）；Wuhan University（武汉大学）；Hunan University of Science and Technology（湖南科技大学）
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）
Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual place. To address this problem, it is crucial to integrate information from only task-relevant regions into image representations. In this paper, we introduce a novel holistic place recognition model, TransVPR, based on vision Transformers. It benefits from the desirable property of the self-attention operation in Transformers which can naturally aggregate task-…
This paper introduces a simple but highly efficient ensemble for robust texture classification, which can effectively deal with translation, scale and changes of significant viewpoint problems. The proposed method first inherits the spirit of spatial pyramid matching model (SPM), which is popular for encoding spatial distribution of local features, but in a flexible way, partitioning the original image into different levels and incorporating different overlapping patterns of each level. This flexible setup helps capture the informative features and produces sufficient local feature codes by so…
École de Technologie Supérieure, University of Québec（魁北克大学高等技术学院）；Instituto Federal do Sul de Minas Gerais（南米纳斯吉拉斯联邦学院）；Pontificia Universidade Catolica do Paraná（巴拉那天主教大学）
Information from an image occurs over multiple and distinct spatial scales. Image pyramid multiresolution representations are a useful data structure for image analysis and manipulation over a spectrum of spatial scales. This paper employs the Gaussian-Laplacian pyramid to treat different spatial frequency bands of a texture separately. First, we generate three images corresponding to three levels of the Gaussian-Laplacian pyramid for an input image to capture intrinsic details. Then we aggregate features extracted from gray and color texture images using bio-inspired texture descriptors, info…
Technicolor（特艺集团）；University of Caen Basse-Normandie（卡昂下诺曼底大学）；ENSICAEN（卡昂国立高等工程师学院）
Deep Convolutional Neural Networks (DCNN) have established a remarkable performance benchmark in the field of image classification, displacing classical approaches based on hand-tailored aggregations of local descriptors. Yet DCNNs impose high computational burdens both at training and at testing time, and training them requires collecting and annotating large amounts of training data. Supervised adaptation methods have been proposed in the literature that partially re-learn a transferred DCNN structure from a new target dataset. Yet these require expensive bounding-box annotations and are sti…
Milsoft（米尔索夫公司）；Inria Grenoble（法国国家信息与自动化研究所格勒诺布尔分院）；Inria Grenoble Rhône-Alpes（法国国家信息与自动化研究所格勒诺布尔-罗纳-阿尔卑斯分院）；Laboratoire Jean Kuntzmann（让·孔茨曼实验室）；CNRS（法国国家科学研究中心）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）
The bag-of-words (BoW) model treats images as sets of local descriptors and represents them by visual word histograms. The Fisher vector (FV) representation extends BoW, by considering the first and second order statistics of local descriptors. In both representations local descriptors are assumed to be identically and independently distributed (iid), which is a poor assumption from a modeling perspective. It has been experimentally observed that the performance of BoW and FV representations can be improved by employing discounting transformations such as power normalization. In this paper, we…
