For successful scene text recognition (STR) models, synthetic text image generators have alleviated the lack of annotated text images from the real world. Specifically, they generate multiple text images with diverse backgrounds, font styles, and text shapes and enable STR models to learn visual patterns that might not be accessible from manually annotated data. In this paper, we introduce a new synthetic text image generator, SynthTIGER, by analyzing techniques used for text image synthesis and integrating effective ones under a single algorithm. Moreover, we propose two techniques that alleviate the long-tail problem in length and character distributions of training data. In our experiments, SynthTIGER achieves better STR performance than the combination of synthetic datasets, MJSynth (MJ) and SynthText (ST). Our ablation study demonstrates the benefits of using sub-components of SynthTIGER and the guideline on generating synthetic text images for STR models. Our implementation is publicly available at https://github.com/clovaai/synthtiger.
Southeast University（东南大学）；University of Oulu（奥卢大学）
In this paper, we investigate the cross-database micro-expression recognition problem, where the training and testing samples are from two different micro-expression databases. Under this setting, the training and testing samples would have different feature distributions and hence the performance of most existing micro-expression recognition methods may decrease greatly. To solve this problem, we propose a simple yet effective method called Target Sample Re-Generator (TSRG) in this paper. By using TSRG, we are able to re-generate the samples from target micro-expression database and the re-ge…
Analyzing the layout of a document to identify headers, sections, tables, figures etc. is critical to understanding its content. Deep learning based approaches for detecting the layout structure of document images have been promising. However, these methods require a large number of annotated examples during training, which are both expensive and time consuming to obtain. We describe here a synthetic document generator that automatically produces realistic documents with labels for spatial positions, extents and categories of the layout elements. The proposed generative process treats every ph…
With the advent of deep learning models, face recognition systems have achieved impressive recognition rates. The workhorses behind this success are Convolutional Neural Networks (CNNs) and the availability of large training datasets. However, we show that small human-imperceptible changes to face samples can evade most prevailing face recognition systems. Even more alarming is the fact that the same generator can be extended to other traits in the future. In this work, we present how such a generator can be trained and also extended to other biometric modalities, such as fingerprint recogniti…
We present the Teacher-Student Generative Adversarial Network (TS-GAN) to generate depth images from single RGB images in order to boost the performance of face recognition systems. For our method to generalize well across unseen datasets, we design two components in the architecture, a teacher and a student. The teacher, which itself consists of a generator and a discriminator, learns a latent mapping between input RGB and paired depth images in a supervised fashion. The student, which consists of two generators (one shared with the teacher) and a discriminator, learns from new RGB data with …
One-shot fine-grained visual recognition often suffers from the problem of training data scarcity for new fine-grained classes. To alleviate this problem, an off-the-shelf image generator can be applied to synthesize additional training images, but these synthesized images are often not helpful for actually improving the accuracy of one-shot fine-grained recognition. This paper proposes a meta-learning framework to combine generated images with original images, so that the resulting ``hybrid'' training images can improve one-shot learning. Specifically, the generic image generator is updated b…
Image degradation due to atmospheric turbulence is common while capturing images at long ranges. To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image. The disentanglement is achieved by decomposing the distortion due to turbulence into blur and deformation components using deblur generator and deformation correction generator respectively. Two paths of restoration are implemented to regularize the disentanglemen…
Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；School of Computer Science, Peking University（北京大学计算机学院）
Facebook AI（Facebook人工智能）；Columbia University（哥伦比亚大学）；Univesity of Edinburgh（爱丁堡大学）
Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost. While this avoids flow computation, it also hurts accuracy since the motion vector is noisy and has substantially reduced resolution, which makes it a less discriminative motion representation. To remedy these issues, we propose a lightweight generator network, which reduces noises in …
Adversarial Masking Contrastive Learning for vein recognition
Chongqing Technology and Business University（重庆工商大学）；Telecom SudParis（巴黎电信学院）；University Paris-Saclay（巴黎-萨克雷大学）；China University of Mining and Technology（中国矿业大学）
Image recognition/classification is a widely studied problem, but its reverse problem, image generation, has drawn much less attention until recently. But the vast majority of current methods for image generation require training/retraining a classifier and/or a generator with certain constraints, which can be hard to achieve. In this paper, we propose a simple approach to directly use a normally trained classifier to generate images. We evaluate our method on MNIST and show that it produces recognizable results for human eyes with limited quality with experiments.
University of Seville（塞维利亚大学）；Vienna University of Technology（维也纳技术大学）；Advanced Technologies Application Center（先进技术应用中心）；University of Bonn（波恩大学）
Structural pattern recognition describes and classifies data based on the relationships of features and parts. Topological invariants, like the Euler number, characterize the structure of objects of any dimension. Cohomology can provide more refined algebraic invariants to a topological space than does homology. It assigns `quantities' to the chains used in homology to characterize holes of any dimension. Graph pyramids can be used to describe subdivisions of the same object at multiple levels of detail. This paper presents cohomology in the context of structural pattern recognition and introd…
Concordia University（康考迪亚大学）；University of Arkansas（阿肯色大学）；VinAI Research（越南人工智能研究院）；North Carolina A&T State University（北卡罗来纳农工州立大学）
Unveiling face images of a subject given his/her high-level representations extracted from a blackbox Face Recognition engine is extremely challenging. It is because the limitations of accessible information from that engine including its structure and uninterpretable extracted features. This paper presents a novel generative structure with Bijective Metric Learning, namely Bijective Generative Adversarial Networks in a Distillation framework (DiBiGAN), for synthesizing faces of an identity given that person's features. In order to effectively address this problem, this work firstly introduces…
Facebook AI Research (FAIR)（Facebook人工智能研究院（FAIR））
Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do…
Facial Expressions Recognition(FER) on low-resolution images is necessary for applications like group expression recognition in crowd scenarios(station, classroom etc.). Classifying a small size facial image into the right expression category is still a challenging task. The main cause of this problem is the loss of discriminative feature due to reduced resolution. Super-resolution method is often used to enhance low-resolution images, but the performance on FER task is limited when on images of very low resolution. In this work, inspired by feature super-resolution methods for object detectio…
In zero-shot learning (ZSL), conditional generators have been widely used to generate additional training features. These features can then be used to train the classifiers for testing data. However, some testing data are considered "hard" as they lie close to the decision boundaries and are prone to misclassification, leading to performance degradation for ZSL. In this paper, we propose to learn clusterable features for ZSL problems. Using a Conditional Variational Autoencoder (CVAE) as the feature generator, we project the original features to a new feature space supervised by an auxiliary c…
Hochschule Darmstadt（达姆施塔特应用科学大学）；Freie Universität Berlin（柏林自由大学）
We present the first method for synthetic generation of contactless fingerprint images, referred to as SynCoLFinGer. To this end, the constituent components of contactless fingerprint images regarding capturing, subject characteristics, and environmental influences are modeled and applied to a synthetically generated ridge pattern using the SFinGe algorithm. The proposed method is able to generate different synthetic samples corresponding to a single finger and it can be parameterized to generate contactless fingerprint images of various quality levels. The resemblance of the synthetically gen…
East China Normal University（华东师范大学）；University of Malaya（马来亚大学）；iFLYTEK（科大讯飞）；Indian Statistical Institute（印度统计研究所）
Scene text recognition is a challenging task due to the complex backgrounds and diverse variations of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention Network (SGBANet) to recognize the texts in scene images. The proposed method first generates the simple semantic feature using Semantic GAN and then recognizes the scene text with the Balanced Attention Module. The Semantic GAN aims to align the semantic feature distribution between the support domain and target domain. Different from the conventional image-to-image translation methods that perform at the im…
Systems that analyse faces have seen significant improvements in recent years and are today used in numerous application scenarios. However, these systems have been found to be negatively affected by facial alterations such as tattoos. To better understand and mitigate the effect of facial tattoos in facial analysis systems, large datasets of images of individuals with and without tattoos are needed. To this end, we propose a generator for automatically adding realistic tattoos to facial images. Moreover, we demonstrate the feasibility of the generation by using a deep learning-based model for…
Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images. Many examples of identities are needed, and for each identity, a large variety of images are needed in order for the network to learn robustness to intra-class variation. In practice, such datasets are difficult to obtain, particularly those containing adequate variation of pose. Generative Adversarial Networks (GANs) provide a potential solution to this problem due to their ability to generate realistic, synthetic images. However, recent studies have shown that current meth…
National University of Singapore（新加坡国立大学）；Fudan University（复旦大学）；Zhejiang Normal University（浙江师范大学）；Indiana University（印第安纳大学）
One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes. To alleviate this problem, off-the-shelf image generation techniques based on Generative Adversarial Networks (GANs) can potentially create additional training images. However, these GAN-generated images are often not helpful for actually improving the accuracy of one-shot fine-grained recognition. In this paper, we propose a meta-learning framework to combine generated images with original images, so that the resulting "hybrid" training images improve one-shot …
Fudan University（复旦大学）；Shanghai University of Engineering Science（上海工程技术大学）
Facial Expression Recognition (FER) suffers from data uncertainties caused by ambiguous facial images and annotators' subjectiveness, resulting in excursive semantic and feature covariate shifting problem. Existing works usually correct mislabeled data by estimating noise distribution, or guide network training with knowledge learned from clean data, neglecting the associative relations of expressions. In this work, we propose an Adaptive Graph-based Feature Normalization (AGFN) method to protect FER models from data uncertainties by normalizing feature distributions with the association of ex…
Static image action recognition, which aims to recognize action based on a single image, usually relies on expensive human labeling effort such as adequate labeled action images and large-scale labeled image dataset. In contrast, abundant unlabeled videos can be economically obtained. Therefore, several works have explored using unlabeled videos to facilitate image action recognition, which can be categorized into the following two groups: (a) enhance visual representations of action images with a designed proxy task on unlabeled videos, which falls into the scope of self-supervised learning; …
Feng Chia University（逢甲大学）；NTUNHS（台湾新竹护理健康大学）；Xiamen University Malaysia（厦门大学马来西亚分校）；Xiamen University（厦门大学）
Owing to the development and advancement of artificial intelligence, numerous works were established in the human facial expression recognition system. Meanwhile, the detection and classification of micro-expressions are attracting attentions from various research communities in the recent few years. In this paper, we first review the processes of a conventional optical-flow-based recognition system, which comprised of facial landmarks annotations, optical flow guided images computation, features extraction and emotion class categorization. Secondly, a few approaches have been proposed to impr…
This work tackles the face recognition task on images captured using thermal camera sensors which can operate in the non-light environment. While it can greatly increase the scope and benefits of the current security surveillance systems, performing such a task using thermal images is a challenging problem compared to face recognition task in the Visible Light Domain (VLD). This is partly due to the much smaller amount number of thermal imagery data collected compared to the VLD data. Unfortunately, direct application of the existing very strong face recognition models trained using VLD data i…
Xiamen University（厦门大学）；Xiamen University of Technology（厦门理工学院）；The University of Adelaide（阿德莱德大学）
Recently, deep learning based facial expression recognition (FER) methods have attracted considerable attention and they usually require large-scale labelled training data. Nonetheless, the publicly available facial expression databases typically contain a small amount of labelled data. In this paper, to overcome the above issue, we propose a novel joint deep learning of facial expression synthesis and recognition method for effective FER. More specifically, the proposed method involves a two-stage learning procedure. Firstly, a facial expression synthesis generative adversarial network (FESGA…
Yonsei University（延世大学）；Fuzhou University（福州大学）；TCL AI Lab（TCL人工智能实验室）；Anhui University（安徽大学）；Tsinghua Shenzhen International Graduate School（清华深圳国际研究生院）
Face recognition based on the deep convolutional neural networks (CNN) shows superior accuracy performance attributed to the high discriminative features extracted. Yet, the security and privacy of the extracted features from deep learning models (deep features) have been often overlooked. This paper proposes the reconstruction of face images from deep features without accessing the CNN network configurations as a constrained optimization problem. Such optimization minimizes the distance between the features extracted from the original face image and the reconstructed face image. Instead of di…
College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；School of Computer Science, The University of Adelaide（阿德莱德大学计算机科学学院）
Generative Adversarial Networks (GAN) have attracted much research attention recently, leading to impressive results for natural image generation. However, to date little success was observed in using GAN generated images for improving classification tasks. Here we attempt to explore, in the context of car license plate recognition, whether it is possible to generate synthetic training data using GAN to improve recognition accuracy. With a carefully-designed pipeline, we show that the answer is affirmative. First, a large-scale image set is generated using the generator of GAN, without manual …
Georgia Institute of Technology（佐治亚理工学院）；Stony Brooks University（石溪大学）
Satisfying the high computation demand of modern deep learning architectures is challenging for achieving low inference latency. The current approaches in decreasing latency only increase parallelism within a layer. This is because architectures typically capture a single-chain dependency pattern that prevents efficient distribution with a higher concurrency (i.e., simultaneous execution of one inference among devices). Such single-chain dependencies are so widespread that even implicitly biases recent neural architecture search (NAS) studies. In this visionary paper, we draw attention to an e…
A major impediment to researchers working in the area of fingerprint recognition is the lack of publicly available, large-scale, fingerprint datasets. The publicly available datasets that do exist contain very few identities and impressions per finger. This limits research on a number of topics, including e.g., using deep networks to learn fixed length fingerprint embeddings. Therefore, we propose PrintsGAN, a synthetic fingerprint generator capable of generating unique fingerprints along with multiple impressions for a given fingerprint. Using PrintsGAN, we synthesize a database of 525k finge…
National Institute of Development Administration（国立发展管理学院）
This work presents a method to predict a geometric surface image from a photograph to assist in image recognition. To recognize objects, several images from different conditions are required for training a model or fine-tuning a pre-trained model. In this work, a geometric surface image is introduced as a better representation than its color image counterpart to overcome lighting conditions. The surface image is predicted from a color image. To do so, the geometric surface image together with its color photographs are firstly trained with Generative Adversarial Networks (GAN) model. The traine…
University of Basel（巴塞尔大学）；Department of Mathematics and Computer Science（数学与计算机科学系）
Recent advances in deep learning have significantly increased the performance of face recognition systems. The performance and reliability of these models depend heavily on the amount and quality of the training data. However, the collection of annotated large datasets does not scale well and the control over the quality of the data decreases with the size of the dataset. In this work, we explore how synthetically generated data can be used to decrease the number of real-world images needed for training deep face recognition systems. In particular, we make use of a 3D morphable face model for …
Samsung Advanced Institute of Technology (SAIT)（三星先进技术研究院）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
As the expressive depth of an emotional face differs with individuals or expressions, recognizing an expression using a single facial image at a moment is difficult. A relative expression of a query face compared to a reference face might alleviate this difficulty. In this paper, we propose to utilize contrastive representation that embeds a distinctive expressive factor for a discriminative purpose. The contrastive representation is calculated at the embedding layer of deep networks by comparing a given (query) image with the reference image. We attempt to utilize a generative reference image…
State-of-the-art offline handwriting text recognition systems tend to use neural networks and therefore require a large amount of annotated data to be trained. In order to partially satisfy this requirement, we propose a system based on Generative Adversarial Networks (GAN) to produce synthetic images of handwritten words. We use bidirectional LSTM recurrent layers to get an embedding of the word to be rendered, and we feed it to the generator network. We also modify the standard GAN by adding an auxiliary network for text recognition. The system is then trained with a balanced combination of …
Given a full fingerprint image (rolled or slap), we present CycleGAN models to generate multiple latent impressions of the same identity as the full print. Our models can control the degree of distortion, noise, blurriness and occlusion in the generated latent print images to obtain Good, Bad and Ugly latent image categories as introduced in the NIST SD27 latent database. The contributions of our work are twofold: (i) demonstrate the similarity of synthetically generated latent fingerprint images to crime scene latents in NIST SD27 and MSP databases as evaluated by the NIST NFIQ 2 quality meas…
Developing consistently well performing visual recognition applications based on convolutional neural networks, e.g. for autonomous driving, is very challenging. One of the obstacles during the development is the opaqueness of their cognitive behaviour. A considerable amount of literature has been published which describes irrational behaviour of trained CNNs showcasing gaps in their cognition. In this paper, a methodology is presented that creates worstcase images using image augmentation techniques. If the CNN's cognitive performance on such images is weak while the augmentation techniques a…
Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University（武汉大学计算机学院多媒体软件国家工程研究中心）；Hubei Key Laboratory of Multimedia and Network Communication Engineering（湖北省多媒体与网络通信工程重点实验室）；Centre for Frontier AI Research (CFAR) & Institute of High Performance Computing (IHPC), A*STAR（新加坡科技研究局前沿人工智能研究中心与高性能计算研究所）；Center for Machine Vision and Signal Analysis (CMVS), University of Oulu（奥卢大学机器视觉与信号分析中心）
