Deep Convolutional Neural Networks (CNN) have shown great success in supervised classification tasks such as character classification or dating. Deep learning methods typically need a lot of annotated training data, which is not available in many scenarios. In these cases, traditional methods are often better than or equivalent to deep learning methods. In this paper, we propose a simple, yet effective, way to learn CNN activation features in an unsupervised manner. Therefore, we train a deep residual network using surrogate classes. The surrogate classes are created by clustering the training dataset, where each cluster index represents one surrogate class. The activations from the penultimate CNN layer serve as features for subsequent classification tasks. We evaluate the feature representations on two publicly available datasets. The focus lies on the ICDAR17 competition dataset on historical document writer identification (Historical-WI). We show that the activation features trained without supervision are superior to descriptors of state-of-the-art writer identification methods. Additionally, we achieve comparable results in the case of handwriting classification using the ICFHR16 competition dataset on historical Latin script types (CLaMM16).
BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval
AIBEX Group, University of Fribourg, Switzerland（AIBEX集团，弗里堡大学，瑞士）；iCoSys Institute, University of Applied Sciences and Arts Western Switzerland（iCoSys研究所，西方瑞士应用科学与艺术大学）；Department of Computational Linguistics, University of Zurich, Switzerland（计算语言学系，苏黎世大学，瑞士）
The analysis of digitized historical manuscripts is typically addressed by paleographic experts. Writer identification refers to the classification of known writers while writer retrieval seeks to find the writer by means of image similarity in a dataset of images. While automatic writer identification/retrieval methods already provide promising results for many historical document types, papyri data is very challenging due to the fiber structures and severe artifacts. Thus, an important step for an improved writer identification is the preprocessing and feature sampling process. We investigat…
FAU Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）；University of West Bohemia（西波希米亚大学）；Sächsische Landesbibliothek, Staats- und Universitätsbibliothek Dresden（萨克森州立图书馆-德累斯顿国家与大学图书馆）
Automatic writer identification is a common problem in document analysis. State-of-the-art methods typically focus on the feature extraction step with traditional or deep-learning-based techniques. In retrieval problems, re-ranking is a commonly used technique to improve the results. Re-ranking refines an initial ranking result by using the knowledge contained in the ranked result, e. g., by exploiting nearest neighbor relations. To the best of our knowledge, re-ranking has not been used for writer identification/retrieval. A possible reason might be that publicly available benchmark datasets …
Towards the Influence of Text Quantity on Writer Retrieval
iCoSys Institute, University of Applied Sciences（iCoSys研究所，应用科学与艺术大学）；Arts Western Switzerland Computer Vision Lab, TU Wien, Austria（西瑞士艺术计算机视觉实验室，维也纳技术大学，奥地利）
Singapore University of Technology and Design（新加坡科技设计大学）；Monash University（蒙纳士大学）；University of Dayton（代顿大学）
In this paper, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH). First, to learn informative representations that can preserve both intra- and inter-modal similarities, we leverage the recent advances in estimating variational lower-bound of MI to maximize the MI between the binary representations and input features and between binary representations of different modalities. By jointly maximizing these MIs under…
This paper addresses writer identification and writer retrieval which is considered as a challenging problem in the document analysis and recognition field. In this work, a novel pipeline is proposed for the problem at hand by employing a unified neural network architecture consisting of the ResNet-20 as a feature extractor and an integrated NetVLAD layer, inspired by the vector of locally aggregated descriptors (VLAD), in the head of the latter part. Having defined this architecture, the triplet semi-hard loss function is used to directly learn an embedding for individual input image patches.…
University of Bari “Aldo Moro”（阿尔多·莫罗巴里大学）；Exprivia S.p.A.（埃克斯普里亚股份公司）
Visual arts are of inestimable importance for the cultural, historic and economic growth of our society. One of the building blocks of most analysis in visual arts is to find similarity relationships among paintings of different artists and painting schools. To help art historians better understand visual arts, this paper presents a framework for visual link retrieval and knowledge discovery in digital painting datasets. Visual link retrieval is accomplished by using a deep convolutional neural network to perform feature extraction and a fully unsupervised nearest neighbor mechanism to retriev…
Recent years have seen the exponential growth of heterogeneous multimedia data. The need for effective and accurate data retrieval from heterogeneous data sources has attracted much research interest in cross-media retrieval. Here, given a query of any media type, cross-media retrieval seeks to find relevant results of different media types from heterogeneous data sources. To facilitate large-scale cross-media retrieval, we propose a novel unsupervised cross-media hashing method. Our method incorporates local affinity and distance repulsion constraints into a matrix factorization framework. Co…
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Institut de Recherche et d’Histoire des Textes（文本研究与历史研究所）；Centre National de la Recherche Scientifique（法国国家科学研究中心）
This competition investigates the performance of large-scale retrieval of historical document images based on writing style. Based on large image data sets provided by cultural heritage institutions and digital libraries, providing a total of 20 000 document images representing about 10 000 writers, divided in three types: writers of (i) manuscript books, (ii) letters, (iii) charters and legal documents. We focus on the task of automatic image retrieval to simulate common scenarios of humanities research, such as writer retrieval. The most teams submitted traditional methods not using deep lea…
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Johannes Gutenberg-Universität Mainz（美因茨约翰内斯·古腾堡大学）；Università degli Studi di Milano（米兰大学）
The type used to print an early modern book can give scholars valuable information about the time and place of its production as well as its producer. Recognizing such type is currently done manually using both the character shapes of `M' or `Qu' and the size of the total type to look it up in a large reference work. This is a reliable method, but it is also slow and requires specific skills. We investigate the performance of type classification and type retrieval using a newly created dataset consisting of easy and difficult types used in early printed books. For type classification, we rely …
Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costly to collect, compared to image-only or text-only data. In this paper, we explore unsupervised Vision-and-Language pre-training (UVLP) to learn the cross-modal representation from non-parallel image and text datasets. We found two key factors that lead to good unsupervised V+L pre-training without parallel data: (i) joint image-and-text input (ii) …
The encoding of local features is an essential part for writer identification and writer retrieval. While CNN activations have already been used as local features in related works, the encoding of these features has attracted little attention so far. In this work, we compare the established VLAD encoding with triangulation embedding. We further investigate generalized max pooling as an alternative to sum pooling and the impact of decorrelation and Exemplar SVMs. With these techniques, we set new standards on two publicly available datasets (ICDAR13, KHATT).
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；omni:us
Handwritten Text Recognition (HTR) is still a challenging problem because it must deal with two important difficulties: the variability among writing styles, and the scarcity of labelled data. To alleviate such problems, synthetic data generation and data augmentation are typically used to train HTR systems. However, training with such data produces encouraging but still inaccurate transcriptions in real words. In this paper, we propose an unsupervised writer adaptation approach that is able to automatically adjust a generic handwritten word recognizer, fully trained with synthetic fonts, towa…
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Institut de Recherche et d’Histoire des Textes (Centre National de la Recherche Scientifique - UPR841)（文本研究与历史研究所（法国国家科学研究中心-UPR841））
This competition succeeds upon a line of competitions for writer and style analysis of historical document images. In particular, we investigate the performance of large-scale retrieval of historical document fragments in terms of style and writer identification. The analysis of historic fragments is a difficult challenge commonly solved by trained humanists. In comparison to previous competitions, we make the results more meaningful by addressing the issue of sample granularity and moving from writer to page fragment retrieval. The two approaches, style and author identification, provide info…
Yandex（扬达克斯）；Lomonosov Moscow State University（莫斯科国立罗蒙诺索夫大学）
We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing state-of-the-art compression methods employ shallow architectures, and we aim to close this gap by our paper. In more detail, we introduce a DNN architecture for the unsupervised compressed-domain retrieval, based on multi-codebook quantization. The proposed architecture is designed to incorporate both fast data encoding and efficient distances computation via…
Hashing has played a pivotal role in large-scale image retrieval. With the development of Convolutional Neural Network (CNN), hashing learning has shown great promise. But existing methods are mostly tuned for classification, which are not optimized for retrieval tasks, especially for instance-level retrieval. In this study, we propose a novel hashing method for large-scale image retrieval. Considering the difficulty in obtaining labeled datasets for image retrieval task in large scale, we propose a novel CNN-based unsupervised hashing method, namely Unsupervised Triplet Hashing (UTH). The uns…
University of Southern California（南加州大学）；Tencent America（腾讯美国）；Tencent Media Lab（腾讯媒体实验室）
An unsupervised point cloud object retrieval and pose estimation method, called PCRP, is proposed in this work. It is assumed that there exists a gallery point cloud set that contains point cloud objects with given pose orientation information. PCRP attempts to register the unknown point cloud object with those in the gallery set so as to achieve content-based object retrieval and pose estimation jointly, where the point cloud registration task is built upon an enhanced version of the unsupervised R-PointHop method. Experiments on the ModelNet40 dataset demonstrate the superior performance of …
We introduce an unsupervised formulation to estimate heteroscedastic uncertainty in retrieval systems. We propose an extension to triplet loss that models data uncertainty for each input. Besides improving performance, our formulation models local noise in the embedding space. It quantifies input uncertainty and thus enhances interpretability of the system. This helps identify noisy observations in query and search databases. Evaluation on both image and video retrieval applications highlight the utility of our approach. We highlight our efficiency in modeling local noise using two real-world …
Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems. By fully exploiting label annotations, they are achieving outstanding retrieval performances compared to the conventional methods. However, it is painstaking to assign labels precisely for a vast amount of training data, and also, the annotation process is error-prone. To tackle these issues, we propose the first deep unsupervised image retrieval method dubbed Self-supervised Product Quantization (SPQ) network, which is label-free and trained in a self-supervised manner. We de…
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positiv…
State Key Laboratory of Management and Control for Complex Systems（复杂系统管理与控制国家重点实验室）；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）
In this paper, we propose a simple but effective semantic part-based weighting aggregation (PWA) for image retrieval. The proposed PWA utilizes the discriminative filters of deep convolutional layers as part detectors. Moreover, we propose the effective unsupervised strategy to select some part detectors to generate the "probabilistic proposals", which highlight certain discriminative parts of objects and suppress the noise of background. The final global PWA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" cor…
Current supervised cross-domain image retrieval methods can achieve excellent performance. However, the cost of data collection and labeling imposes an intractable barrier to practical deployment in real applications. In this paper, we investigate the unsupervised cross-domain image retrieval task, where class labels and pairing annotations are no longer a prerequisite for training. This is an extremely challenging task because there is no supervision for both in-domain feature representation learning and cross-domain alignment. We address both challenges by introducing: 1) a new cluster-wise …
Unsupervised image retrieval aims to learn an efficient retrieval system without expensive data annotations, but most existing methods rely heavily on handcrafted feature descriptors or pre-trained feature extractors. To minimize human supervision, recent advance proposes deep fully unsupervised image retrieval aiming at training a deep model from scratch to jointly optimize visual features and quantization codes. However, existing approach mainly focuses on instance contrastive learning without considering underlying semantic structure information, resulting in sub-optimal performance. In thi…
College of Computer Science, Sichuan University（四川大学计算机科学学院）；Centre for Frontier AI Research (CFAR), A*STAR（新加坡科技研究局前沿人工智能研究中心）
Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. This paper studies a less-touched problem of cross-domain image retrieval, i.e., unsupervised cross-domain image retrieval, considering the following practical assumptions: (i) no correspondence relationship, and (ii) no category annotations. It is challenging to align and bridge distinct domains without cross-domain correspondence. To tackle the challenge, we present a novel Correspondence-free Domain Alignment (CoDA) method to effectively el…
National University of Singapore（新加坡国立大学）；University of Edinburgh（爱丁堡大学）；University of Surrey（萨里大学）
The practical value of existing supervised sketch-based image retrieval (SBIR) algorithms is largely limited by the requirement for intensive data collection and labeling. In this paper, we present the first attempt at unsupervised SBIR to remove the labeling cost (both category annotations and sketch-photo pairings) that is conventionally needed for training. Existing single-domain unsupervised representation learning methods perform poorly in this application, due to the unique cross-domain (sketch and photo) nature of the problem. We therefore introduce a novel framework that simultaneously…
Studies show that Deep Neural Network (DNN)-based image classification models are vulnerable to maliciously constructed adversarial examples. However, little effort has been made to investigate how DNN-based image retrieval models are affected by such attacks. In this paper, we introduce Unsupervised Adversarial Attacks with Generative Adversarial Networks (UAA-GAN) to attack deep feature-based image retrieval systems. UAA-GAN is an unsupervised learning model that requires only a small amount of unlabeled data for training. Once trained, it produces query-specific perturbations for query imag…
University of Toronto（多伦多大学）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；Vector Institute（矢量研究所）；Peter Munk Cardiac Centre（彼得·蒙克心脏中心）
Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold. However, existing diffusion methods suffer from three major limitations: 1) they usually rely on local structures without considering global manifold information; 2) they focus on improving pair-wise similarities within existing images input output transductively while lacking flexibility to learn representations for novel unseen instances inductively; 3) they fail to scale to large datasets due to prohibitive memory consumption and computational…
Due to the availability of large-scale multi-modal data (e.g., satellite images acquired by different sensors, text sentences, etc) archives, the development of cross-modal retrieval systems that can search and retrieve semantically relevant data across different modalities based on a query in any modality has attracted great attention in RS. In this paper, we focus our attention on cross-modal text-image retrieval, where queries from one modality (e.g., text) can be matched to archive entries from another (e.g., image). Most of the existing cross-modal text-image retrieval systems require a h…
The development of cross-modal retrieval systems that can search and retrieve semantically relevant data across different modalities based on a query in any modality has attracted great attention in remote sensing (RS). In this paper, we focus our attention on cross-modal text-image retrieval, where queries from one modality (e.g., text) can be matched to archive entries from another (e.g., image). Most of the existing cross-modal text-image retrieval systems in RS require a high number of labeled training samples and also do not allow fast and memory-efficient retrieval. These issues limit th…
Inria Grenoble Rhone-Alpes（法国国家信息与自动化研究所格勒诺布尔-罗讷阿尔卑斯分院）；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）
Convolutional neural networks (CNNs) have recently received a lot of attention due to their ability to model local stationary structures in natural images in a multi-scale fashion, when learning all model parameters with supervision. While excellent performance was achieved for image classification when large amounts of labeled visual data are available, their success for un-supervised tasks such as image retrieval has been moderate so far. Our paper focuses on this latter setting and explores several methods for learning patch descriptors without supervision with application to matching and i…
The vast increase in amount and complexity of digital content led to a wide interest in ad-hoc retrieval systems in recent years. Complementary, the existence of heterogeneous data sources and retrieval models stimulated the proliferation of increasingly ingenious and effective rank aggregation functions. Although recently proposed rank aggregation functions are promising with respect to effectiveness, existing proposals in the area usually overlook efficiency aspects. We propose an innovative rank aggregation function that is unsupervised, intrinsically multimodal, and targeted for fast retri…
Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection
College of Artificial Intelligence, Nankai University, China（南开大学人工智能学院）；Department of Computing, The Hong Kong Polytechnic University, Hong Kong（香港理工大学计算机系）；School of Computer and Information, Anhui Normal University, China（安徽师范大学计算机与信息学院）
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…
Text-Phase Synergy Network with Dual Priors for Unsupervised Cross-Domain Image Retrieval
School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（教育部新一代人工智能技术及其跨学科应用重点实验室（东南大学））
Centre Tecnològic de Catalunya（加泰罗尼亚技术中心）；Computer Vision Center（计算机视觉中心）；University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Huawei Research（华为研究院）
Image to image translation aims to learn a mapping that transforms an image from one visual domain to another. Recent works assume that images descriptors can be disentangled into a domain-invariant content representation and a domain-specific style representation. Thus, translation models seek to preserve the content of source images while changing the style to a target visual domain. However, synthesizing new images is extremely challenging especially in multi-domain translations, as the network has to compose content and style to generate reliable and diverse images in multiple domains. In …
Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval. Compared with unsupervised hashing, supervised hashing methods for labeled data have usually better performance by utilizing semantic label information. Intuitively, for unlabeled data, it will improve the performance of unsupervised hashing methods if we can first mine some supervised semantic 'label information' from unlabeled data and then incorporate the 'label information' into the training process. Thus, in this paper, we propose a novel Object Detection based Deep Unsupervised …
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning approaches have succeeded in obtaining features appropriate for classification of multimedia data. However, unsupervised learning of feature representations adapted to content-based matching, comparison, or retrieval of multimedia data has not been explored well. To obtain such retrieval-adapted features, we introduce the idea of combining diffusion distance on a…
Lahore University of Management Sciences（拉合尔管理科学大学）
The advent of deep perceptual networks brought about a paradigm shift in machine vision and image perception. Image apprehension lately carried out by hand-crafted features in the latent space have been replaced by deep features acquired from supervised networks for improved understanding. However, such deep networks require strict supervision with a substantial amount of the labeled data for authentic training process. These methods perform poorly in domains lacking labeled data especially in case of remote sensing image retrieval. Resolving this, we propose an unsupervised encoder-decoder fe…
In recent years, deep hashing methods have been proved to be efficient since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In real-world application, it is a time-consuming and overloaded task for annotating a large number of images. In this paper, we propose a novel unsupervised deep hashing method for large-scale image retrieval. Our method, namely unsupervised semantic deep hashing (\textbf{USDH}), uses semantic information preserved in the CNN feature layer to guide the training of network. We enfor…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-尚佩恩分校）；Google Research（谷歌研究院）
We present Retrieve in Style (RIS), an unsupervised framework for facial feature transfer and retrieval on real images. Recent work shows capabilities of transferring local facial features by capitalizing on the disentanglement property of the StyleGAN latent space. RIS improves existing art on the following: 1) Introducing more effective feature disentanglement to allow for challenging transfers (ie, hair, pose) that were not shown possible in SoTA methods. 2) Eliminating the need for per-image hyperparameter tuning, and for computing a catalog over a large batch of images. 3) Enabling fine-g…
Inria Rennes VRG, FEE, CTU in Prague（法国国家信息与自动化研究所雷恩分所VRG、费尔科学院（FEE）、捷克技术大学布拉格分校（CTU in Prague））；Inria（法国国家信息与自动化研究所）；CTU in Prague（捷克技术大学布拉格分校）
Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative an…
