We present a domain adaption framework to address a domain mismatch between synthetic training and real-world testing data. We demonstrate our method on a challenging fine-grain classification problem: recognizing a font style from an image of text. In this task, it is very easy to generate lots of rendered font examples but very hard to obtain real-world labeled images. This real-to-synthetic domain gap caused poor generalization to new real data in previous font recognition methods (Chen et al. (2014)). In this paper, we introduce a Convolutional Neural Network decomposition approach, leveraging a large training corpus of synthetic data to obtain effective features for classification. This is done using an adaptation technique based on a Stacked Convolutional Auto-Encoder that exploits a large collection of unlabeled real-world text images combined with synthetic data preprocessed in a specific way. The proposed DeepFont method achieves an accuracy of higher than 80% (top-5) on a new large labeled real-world dataset we collected.
Recognizing fonts has become an important task in document analysis, due to the increasing number of available digital documents in different fonts and emphases. A generic font-recognition system independent of language, script and content is desirable for processing various types of documents. At the same time, categorizing calligraphy styles in handwritten manuscripts is important for palaeographic analysis, but has not been studied sufficiently in the literature. We address the font-recognition problem as analysis and categorization of textures. We extract features using complex wavelet tra…
Beckman Institute for Advanced Science and Technology（贝克曼高等科学技术研究所）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Adobe Research（Adobe研究院）
We address a challenging fine-grain classification problem: recognizing a font style from an image of text. In this task, it is very easy to generate lots of rendered font examples but very hard to obtain real-world labeled images. This real-to-synthetic domain gap caused poor generalization to new real data in previous methods (Chen et al. (2014)). In this paper, we refer to Convolutional Neural Networks, and use an adaptation technique based on a Stacked Convolutional Auto-Encoder that exploits unlabeled real-world images combined with synthetic data. The proposed method achieves an accuracy…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Adobe Research（奥多比研究院）；Snapchat Inc（Snapchat公司）；Google Inc（谷歌公司）
As font is one of the core design concepts, automatic font identification and similar font suggestion from an image or photo has been on the wish list of many designers. We study the Visual Font Recognition (VFR) problem, and advance the state-of-the-art remarkably by developing the DeepFont system. First of all, we build up the first available large-scale VFR dataset, named AdobeVFR, consisting of both labeled synthetic data and partially labeled real-world data. Next, to combat the domain mismatch between available training and testing data, we introduce a Convolutional Neural Network (CNN) …
Although lots of progress were made in Text Recognition/OCR in recent years, the task of font recognition is remaining challenging. The main challenge lies in the subtle difference between these similar fonts, which is hard to distinguish. This paper proposes a novel font recognizer with a pluggable module solving the font recognition task. The pluggable module hides the most discriminative accessible features and forces the network to consider other complicated features to solve the hard examples of similar fonts, called HE Block. Compared with the available public font recognition systems, o…
Chinese font recognition (CFR) has gained significant attention in recent years. However, due to the sparsity of labeled font samples and the structural complexity of Chinese characters, CFR is still a challenging task. In this paper, a DropRegion method is proposed to generate a large number of stochastic variant font samples whose local regions are selectively disrupted and an inception font network (IFN) with two additional convolutional neural network (CNN) structure elements, i.e., a cascaded cross-channel parametric pooling (CCCP) and global average pooling, is designed. Because the dist…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Scene text recognition (STR) has been extensively studied in last few years. Many recently-proposed methods are specially designed to accommodate the arbitrary shape, layout and orientation of scene texts, but ignoring that various font (or writing) styles also pose severe challenges to STR. These methods, where font features and content features of characters are tangled, perform poorly in text recognition on scene images with texts in novel font styles. To address this problem, we explore font-independent features of scene texts via attentional generation of glyphs in a large number of font …
OCR algorithms have received a significant improvement in performance recently, mainly due to the increase in the capabilities of artificial intelligence algorithms. However, this advancement is not evenly distributed over all languages. Urdu is among the languages which did not receive much attention, especially in the font independent perspective. There exists no automated system that can reliably recognize printed Urdu text in images and videos across different fonts. To help bridge this gap, we have developed Qaida, a large scale data set with 256 fonts, and a complete Urdu lexicon. We hav…
Friedrich Schiller University Jena（耶拿弗里德里希·席勒大学）；German Aerospace Center (DLR)（德国航空航天中心）
Deep-learning methods offer unsurpassed recognition performance in a wide range of domains, including fine-grained recognition tasks. However, in most problem areas there are insufficient annotated training samples. Therefore, the topic of transfer learning respectively domain adaptation is particularly important. In this work, we investigate to what extent unsupervised domain adaptation can be used for fine-grained recognition in a biodiversity context to learn a real-world classifier based on idealized training data, e.g. preserved butterflies and plants. Moreover, we investigate the influen…
In this paper, we have extensively investigated the unconstrained ear recognition problem. We have first shown the importance of domain adaptation, when deep convolutional neural network models are used for ear recognition. To enable domain adaptation, we have collected a new ear dataset using the Multi-PIE face dataset, which we named as Multi-PIE ear dataset. To improve the performance further, we have combined different deep convolutional neural network models. We have analyzed in depth the effect of ear image quality, for example illumination and aspect ratio, on the classification perform…
In this paper a novel approach is proposed based on single Euler number feature which is free from thinning and size normalization for multi-font and multi-size Kannada numeral recognition system. A nearest neighbor classification is used for classification of Kannada numerals by considering the Euclidian distance. A total 1500 numeral images with different font sizes between (10..84) are tested for algorithm efficiency and the overall the classification accuracy is found to be 99.00% .The said method is thinning free, fast, and showed encouraging results on varying font styles and sizes of Ka…
Since annotating and curating large datasets is very expensive, there is a need to transfer the knowledge from existing annotated datasets to unlabelled data. Data that is relevant for a specific application, however, usually differs from publicly available datasets since it is sampled from a different domain. While domain adaptation methods compensate for such a domain shift, they assume that all categories in the target domain are known and match the categories in the source domain. Since this assumption is violated under real-world conditions, we propose an approach for open set domain adap…
Automatic surgical activity recognition enables more intelligent surgical devices and a more efficient workflow. Integration of such technology in new operating rooms has the potential to improve care delivery to patients and decrease costs. Recent works have achieved a promising performance on surgical activity recognition; however, the lack of generalizability of these models is one of the critical barriers to the wide-scale adoption of this technology. In this work, we study the generalizability of surgical activity recognition models across operating rooms. We propose a new domain adaptati…
We propose TrueType Transformer (T3), which can perform character and font style recognition in an outline format. The outline format, such as TrueType, represents each character as a sequence of control points of stroke contours and is frequently used in born-digital documents. T3 is organized by a deep neural network, so-called Transformer. Transformer is originally proposed for sequential data, such as text, and therefore appropriate for handling the outline data. In other words, T3 directly accepts the outline data without converting it into a bitmap image. Consequently, T3 realizes a reso…
In this paper a fast and novel method is proposed for multi-font multi-size Kannada numeral recognition which is thinning free and without size normalization approach. The different structural feature are used for numeral recognition namely, directional density of pixels in four directions, water reservoirs, maximum profile distances, and fill hole density are used for the recognition of Kannada numerals. A Euclidian minimum distance criterion is used to find minimum distances and K-nearest neighbor classifier is used to classify the Kannada numerals by varying the size of numeral image from 1…
Real-world face recognition using a single sample per person (SSPP) is a challenging task. The problem is exacerbated if the conditions under which the gallery image and the probe set are captured are completely different. To address these issues from the perspective of domain adaptation, we introduce an SSPP domain adaptation network (SSPP-DAN). In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversarial training. However, the SSPP characteristic of one training sample per class is insufficient to …
While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in every new scenario, a task that is infeasible. However, sources such as e-commerce websites and field guides provide annotated images for many classes. In this work, we study fine-grained domain adaptation as a step towards overcoming the dataset shift between easily acquired annotated images and the real world. Adaptation has not been studied in the fine-gr…
Gulbarga University（古尔伯加大学）；Karnatak Arts, Science and Commerce College（卡纳塔克艺术与科学商业学院）
This paper presents multi-font/multi-size Kannada numerals and vowels recognition based on spatial features. Directional spatial features viz stroke density, stroke length and the number of stokes in an image are employed as potential features to characterize the printed Kannada numerals and vowels. Based on these features 1100 numerals and 1400 vowels are classified with Multi-class Support Vector Machines (SVM). The proposed system achieves the recognition accuracy as 98.45% and 90.64% for numerals and vowels respectively.
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Nanyang Technological University（南洋理工大学）
Video-based Unsupervised Domain Adaptation (VUDA) methods improve the robustness of video models, enabling them to be applied to action recognition tasks across different environments. However, these methods require constant access to source data during the adaptation process. Yet in many real-world applications, subjects and scenes in the source video domain should be irrelevant to those in the target video domain. With the increasing emphasis on data privacy, such methods that require source data access would raise serious privacy issues. Therefore, to cope with such concern, a more practica…
University of Science and Technology of China（中国科学技术大学）
Current facial expression recognition methods fail to simultaneously cope with pose and subject variations. In this paper, we propose a novel unsupervised adversarial domain adaptation method which can alleviate both variations at the same time. Specially, our method consists of three learning strategies: adversarial domain adaptation learning, cross adversarial feature learning, and reconstruction learning. The first aims to learn pose- and expression-related feature representations in the source domain and adapt both feature distributions to that of the target domain by imposing adversarial …
Fine-grained action recognition datasets exhibit environmental bias, where multiple video sequences are captured from a limited number of environments. Training a model in one environment and deploying in another results in a drop in performance due to an unavoidable domain shift. Unsupervised Domain Adaptation (UDA) approaches have frequently utilised adversarial training between the source and target domains. However, these approaches have not explored the multi-modal nature of video within each domain. In this work we exploit the correspondence of modalities as a self-supervised alignment a…
Recent adversarial learning research has achieved very impressive progress for modelling cross-domain data shifts in appearance space but its counterpart in modelling cross-domain shifts in geometry space lags far behind. This paper presents an innovative Geometry-Aware Domain Adaptation Network (GA-DAN) that is capable of modelling cross-domain shifts concurrently in both geometry space and appearance space and realistically converting images across domains with very different characteristics. In the proposed GA-DAN, a novel multi-modal spatial learning technique is designed which converts a …
This report describes the technical details of our submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition. The EPIC-Kitchens dataset is more difficult than other video domain adaptation datasets due to multi-tasks with more modalities. Firstly, to participate in the challenge, we employ a transformer to capture the spatial information from each modality. Secondly, we employ a temporal attention module to model temporal-wise inter-dependency. Thirdly, we employ the adversarial domain adaptation network to learn the general features between labeled s…
The University of British Columbia（不列颠哥伦比亚大学）；Southern University of Science and Technology（南方科技大学）
Detection and recognition of staircase as upstairs, downstairs and negative (e.g., ladder) are the fundamental of assisting the visually impaired to travel independently in unfamiliar environments. Previous researches have focused on using massive amounts of RGB-D scene data to train traditional machine learning (ML) based models to detect and recognize the staircase. However, the performance of traditional ML techniques is limited by the amount of labeled RGB-D staircase data. In this paper, we apply an unsupervised domain adaptation approach in deep architectures to transfer knowledge learne…
Though unsupervised domain adaptation (UDA) has achieved very impressive progress recently, it remains a great challenge due to missing target annotations and the rich discrepancy between source and target distributions. We propose Spectral UDA (SUDA), an effective and efficient UDA technique that works in the spectral space and can generalize across different visual recognition tasks. SUDA addresses the UDA challenges from two perspectives. First, it introduces a spectrum transformer (ST) that mitigates inter-domain discrepancies by enhancing domain-invariant spectra while suppressing domain-…
In this paper, we consider the problem of detecting counterfeit identity documents in images captured with smartphones. As the number of documents contain special fonts, we study the applicability of convolutional neural networks (CNNs) for detection of the conformance of the fonts used with the ones, corresponding to the government standards. Here, we use multi-task learning to differentiate samples by both fonts and characters and compare the resulting classifier with its analogue trained for binary font classification. We train neural networks for authenticity estimation of the fonts used i…
University of Trento（特伦托大学）；Universidade Federal do Espírito Santo（圣埃斯皮里图联邦大学）；University of Verona（维罗纳大学）；Istituto Italiano di Tecnologia（意大利技术研究院）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Over the last few years, Unsupervised Domain Adaptation (UDA) techniques have acquired remarkable importance and popularity in computer vision. However, when compared to the extensive literature available for images, the field of videos is still relatively unexplored. On the other hand, the performance of a model in action recognition is heavily affected by domain shift. In this paper, we propose a simple and novel UDA approach for video action recognition. Our approach leverages recent advances on spatio-temporal transformers to build a robust source model that better generalises to the targe…
Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target and source domains without the requirement of meaningful metrics across domains. In addition, the proposal can associate the correct mapping between source and target domains and guarantee a constraint of topology between source and target domains. The proposed method is evaluated on different datasets in various problems, i.e. (i) digit recognition on MNIS…
Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperform on images from unseen geographies. We investigate the effectiveness of unsupervised domain adaptation (UDA) of such models across geographies at closing this performance gap. To do so, we first curate two shifts from existing datasets to study the Geographical DA problem, and discover new challenges beyond data distribution shift: context shift, wherein object surroundings may change significantly across geograph…
Texture or Semantics? Vision-Language Models Get Lost in Font Recognition
University of California, San Diego（加州大学圣地亚哥分校）；ByteDance（字节跳动）；The University of Queensland（昆士兰大学）；University of Southern California（南加州大学）；University at Buffalo（布法罗大学）；University of California, Merced（加州大学默塞德分校）
MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition
Institute of Computer Science, ZHAW（苏黎世应用科技大学计算机科学学院）；People and Computing Laboratory, University of Zurich（苏黎世大学人与计算实验室）；Centre for Artificial Intelligence, ZHAW（苏黎世应用科技大学人工智能中心）；European Centre for Living Technology (ECLT)（欧洲生命技术中心）
NEC Labs America（NEC美国实验室）；UC Merced（加州大学默塞德分校）；Dalian University of Technology（大连理工大学）；UC San Diego（加州大学圣迭戈分校）
Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual quality between the domains and the difficulty of curating diverse large-scale video datasets. This paper addresses both of those challenges, through an image to video feature-level domain adaptation approach, to learn discriminative video frame representations. The framework utilizes large-scale unlabeled video data to reduce the gap between different domains while transferring discriminative …
Waseda University（早稻田大学）；The National Institute of Advanced Industrial Science and Technology（产业技术综合研究所）
In this study, a perceptually hidden object-recognition method is investigated to generate secure images recognizable by humans but not machines. Hence, both the perceptual information hiding and the corresponding object recognition methods should be developed. Block-wise image scrambling is introduced to hide perceptual information from a third party. In addition, an adaptation network is proposed to recognize those scrambled images. Experimental comparisons conducted using CIFAR datasets demonstrated that the proposed adaptation network performed well in incorporating simple perceptual infor…
Shanghai Jiao Tong University（上海交通大学）；Beijing Institute of Technology（北京理工大学）
In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced…
Centre for Vision Information Technology International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院视觉信息技术中心）
Scene-text recognition is remarkably better in Latin languages than the non-Latin languages due to several factors like multiple fonts, simplistic vocabulary statistics, updated data generation tools, and writing systems. This paper examines the possible reasons for low accuracy by comparing English datasets with non-Latin languages. We compare various features like the size (width and height) of the word images and word length statistics. Over the last decade, generating synthetic datasets with powerful deep learning techniques has tremendously improved scene-text recognition. Several control…
It has been well proved that deep networks are efficient at extracting features from a given (source) labeled dataset. However, it is not always the case that they can generalize well to other (target) datasets which very often have a different underlying distribution. In this report, we evaluate four different domain adaptation techniques for image classification tasks: DeepCORAL, DeepDomainConfusion, CDAN and CDAN+E. These techniques are unsupervised given that the target dataset dopes not carry any labels during training phase. We evaluate model performance on the office-31 dataset. A link …
We propose a new metric to measure domain divergence and a new domain adaptation method for time-series classification. The metric belongs to the class of probability distributions-based metrics, is transductive, and does not assume the presence of source data samples. The 2-stage method utilizes an improved autoregressive, RNN-based architecture with deep/non-linear transformation. We assess our metric and the performance of our model in the context of sEMG/EMG-based gesture recognition under inter-session and inter-subject domain shifts.
BMW Group（宝马集团）；Technical University of Munich（慕尼黑工业大学）；University of Glasgow（格拉斯哥大学）；Radboud University（拉德堡德大学）
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense point clouds and performance drops significantly for sparse point clouds. Unsupervised domain adaption allows to minimise the discrepancy between dense and sparse point clouds with minimal unlabelled sparse point clouds, thereby saving additional sparse data collection, annotation and retraining costs. In this work, we propose a novel method for point cloud b…
Due to the numerous potential applications in visual surveillance and nighttime driving, recognizing human action in low-light conditions remains a difficult problem in computer vision. Existing methods separate action recognition and dark enhancement into two distinct steps to accomplish this task. However, isolating the recognition and enhancement impedes end-to-end learning of the space-time representation for video action classification. This paper presents a domain adaptation-based action recognition approach that uses adversarial learning in cross-domain settings to learn cross-domain ac…
Given labeled data in a source domain, unsupervised domain adaptation has been widely adopted to generalize models for unlabeled data in a target domain, whose data distributions are different. However, existing works are inapplicable to face recognition under privacy constraints because they require sharing of sensitive face images between domains. To address this problem, we propose federated unsupervised domain adaptation for face recognition, FedFR. FedFR jointly optimizes clustering-based domain adaptation and federated learning to elevate performance on the target domain. Specifically, f…
TU Wien（维也纳工业大学）；Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利理工学院）
Unsupervised Domain Adaptation (DA) exploits the supervision of a label-rich source dataset to make predictions on an unlabeled target dataset by aligning the two data distributions. In robotics, DA is used to take advantage of automatically generated synthetic data, that come with "free" annotation, to make effective predictions on real data. However, existing DA methods are not designed to cope with the multi-modal nature of RGB-D data, which are widely used in robotic vision. We propose a novel RGB-D DA method that reduces the synthetic-to-real domain shift by exploiting the inter-modal rel…
Face recognition (FR) is the most preferred mode for biometric-based surveillance, due to its passive nature of detecting subjects, amongst all different types of biometric traits. FR under surveillance scenario does not give satisfactory performance due to low contrast, noise and poor illumination conditions on probes, as compared to the training samples. A state-of-the-art technology, Deep Learning, even fails to perform well in these scenarios. We propose a novel soft-margin based learning method for multiple feature-kernel combinations, followed by feature transformed using Domain Adaptati…
Al Imam Mohammad Ibn Saud Islamic University（伊玛目穆罕默德·本·沙特伊斯兰大学）；Cairo University（开罗大学）
Arabic language is one of the most popular languages in the world. Hundreds of millions of people in many countries around the world speak Arabic as their native speaking. However, due to complexity of Arabic language, recognition of printed and handwritten Arabic text remained untouched for a very long time compared with English and Chinese. Although, in the last few years, significant number of researches has been done in recognizing printed and handwritten Arabic text, it stills an open research field due to cursive nature of Arabic script. This paper proposes automatic printed Arabic text …
University of Rochester（罗切斯特大学）；Adobe Research（Adobe研究院）
Font selection is one of the most important steps in a design workflow. Traditional methods rely on ordered lists which require significant domain knowledge and are often difficult to use even for trained professionals. In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively. We collect a large-scale font tagging dataset of high-quality professional fonts. The dataset contains nearly 20,000 fonts, 2,000 tags, and hundreds of thousands of font-tag…
Optical Character Recognition (OCR) is the process of extracting digitized text from images of scanned documents. While OCR systems have already matured in many languages, they still have shortcomings in cursive languages with overlapping letters such as the Arabic language. This paper proposes a complete Arabic OCR system that takes a scanned image of Arabic Naskh script as an input and generates a corresponding digital document. Our Arabic OCR system consists of the following modules: Pre-processing, Word-level Feature Extraction, Character Segmentation, Character Recognition, and Post-proce…
