Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis
Johns Hopkins University（约翰霍普金斯大学）；University of Nebraska（内布拉斯加大学）；U.S. Army DEVCOM Army Research Laboratory (ARL)（美国陆军DEVCOM陆军研究实验室）；Booz Allen Hamilton（博思艾伦汉密尔顿公司）
Xing Di, Benjamin S. Riggan, Shuowen Hu, Nathaniel J. Short, Vishal M. Patel
备注：
accepted by IEEE Transactions on Biometrics, Behavior, and Identity Science (T-BIOM). arXiv admin note: substantial text overlap with arXiv:1901.00889
Thermal-to-visible face verification is a challenging problem due to the large domain discrepancy between the modalities. Existing approaches either attempt to synthesize visible faces from thermal faces or learn domain-invariant robust features from these modalities for cross-modal matching. In this paper, we use attributes extracted from visible images to synthesize attribute-preserved visible images from thermal imagery for cross-modal matching. A pre-trained attribute predictor network is used to extract the attributes from the visible image. Then, a novel multi-scale generator is proposed to synthesize the visible image from the thermal image guided by the extracted attributes. Finally, a pre-trained VGG-Face network is leveraged to extract features from the synthesized image and the input visible image for verification. Extensive experiments evaluated on three datasets (ARL Face Database, Visible and Thermal Paired Face Database, and Tufts Face Database) demonstrate that the proposed method achieves state-of-the-art performance. In particular, it achieves around 2.41\%, 2.85\% and 1.77\% improvements in Equal Error Rate (EER) over the state-of-the-art methods on the ARL Face Database, Visible and Thermal Paired Face Database, and Tufts Face Database, respectively. An extended dataset (ARL Face Dataset volume III) consisting of polarimetric thermal faces of 121 subjects is also introduced in this paper. Furthermore, an ablation study is conducted to demonstrate the effectiveness of different modules in the proposed method.
MUKH Technologies（MUKH科技公司）；University of Maryland（马里兰大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Georgia（佐治亚大学）
In recent years, visible-spectrum face verification systems have been shown to match the performance of experienced forensic examiners. However, such systems are ineffective in low-light and nighttime conditions. Thermal face imagery, which captures body heat emissions, effectively augments the visible spectrum, capturing discriminative facial features in scenes with limited illumination. Due to the increased cost and difficulty of obtaining diverse, paired thermal and visible spectrum datasets, not many algorithms and large-scale benchmarks for low-light recognition are available. This paper …
Johns Hopkins University（约翰斯·霍普金斯大学）；Univ. of Maryland, College Park（马里兰大学帕克分校）；NIST（美国国家标准与技术研究院）
Face recognition networks generally demonstrate bias with respect to sensitive attributes like gender, skintone etc. For gender and skintone, we observe that the regions of the face that a network attends to vary by the category of an attribute. This might contribute to bias. Building on this intuition, we propose a novel distillation-based approach called Distill and De-bias (D&D) to enforce a network to attend to similar face regions, irrespective of the attribute category. In D&D, we train a teacher network on images from one category of an attribute; e.g. light skintone. Then distilling in…
Dalian University of Technology（大连理工大学）；Peng Cheng Laboratory（鹏城实验室）；Tiwaki Co.Ltd.（Tiwaki有限公司）
With the popularity of multi-modal sensors, visible-thermal (RGB-T) object tracking is to achieve robust performance and wider application scenarios with the guidance of objects' temperature information. However, the lack of paired training samples is the main bottleneck for unlocking the power of RGB-T tracking. Since it is laborious to collect high-quality RGB-T sequences, recent benchmarks only provide test sequences. In this paper, we construct a large-scale benchmark with high diversity for visible-thermal UAV tracking (VTUAV), including 500 sequences with 1.7 million high-resolution (192…
Jawaharlal Nehru University（贾瓦哈拉尔·尼赫鲁大学）；Indian Institute of Technology Delhi（印度理工学院德里分校）
Predicting attributes in the landmark free facial images is itself a challenging task which gets further complicated when the face gets occluded due to the usage of masks. Smart access control gates which utilize identity verification or the secure login to personal electronic gadgets may utilize face as a biometric trait. Particularly, the Covid-19 pandemic increasingly validates the essentiality of hygienic and contactless identity verification. In such cases, the usage of masks become more inevitable and performing attribute prediction helps in segregating the target vulnerable groups from …
West Virginia University（西弗吉尼亚大学）；DEVCOM Army Research Laboratory（美国陆军作战能力发展司令部陆军研究实验室）；Booz Allen Hamilton（博思艾伦汉密尔顿）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Nebraska-Lincoln（内布拉斯加大学林肯分校）
Thermal face imagery, which captures the naturally emitted heat from the face, is limited in availability compared to face imagery in the visible spectrum. To help address this scarcity of thermal face imagery for research and algorithm development, we present the DEVCOM Army Research Laboratory Visible-Thermal Face Dataset (ARL-VTF). With over 500,000 images from 395 subjects, the ARL-VTF dataset represents, to the best of our knowledge, the largest collection of paired visible and thermal face images to date. The data was captured using a modern long wave infrared (LWIR) camera mounted along…
In this paper the intermediary visual content verification method based on multi-level co-occurrences is studied. The co-occurrence statistics are in general used to determine relational properties between objects based on information collected from data. As such these measures are heavily subject to relative number of occurrences and give only limited amount of accuracy when predicting objects in real world. In order to improve the accuracy of this method in the verification task, we include the context information such as location, type of environment etc. In order to train our model we prov…
Thermal to visible face verification is a challenging problem due to the large domain discrepancy between the modalities. Existing approaches either attempt to synthesize visible faces from thermal faces or extract robust features from these modalities for cross-modal matching. In this paper, we take a different approach in which we make use of the attributes extracted from the visible image to synthesize the attribute-preserved visible image from the input thermal image for cross-modal matching. A pre-trained VGG-Face network is used to extract the attributes from the visible image. Then, a n…
Johns Hopkins University（约翰斯·霍普金斯大学）；U.S. Army CCDC Army Research Laboratory（美国陆军CCDC陆军研究实验室）
Polarimetric thermal to visible face verification entails matching two images that contain significant domain differences. Several recent approaches have attempted to synthesize visible faces from thermal images for cross-modal matching. In this paper, we take a different approach in which rather than focusing only on synthesizing visible faces from thermal faces, we also propose to synthesize thermal faces from visible faces. Our intuition is based on the fact that thermal images also contain some discriminative information about the person for verification. Deep features from a pre-trained C…
Beijing Institute of Technology（北京理工大学）；Yantai IRay Technologies Lt. Co.（烟台艾睿光电科技有限公司）
Infrared cameras are often utilized to enhance the night vision since the visible light cameras exhibit inferior efficacy without sufficient illumination. However, infrared data possesses inadequate color contrast and representation ability attributed to its intrinsic heat-related imaging principle. This makes it arduous to capture and analyze information for human beings, meanwhile hindering its application. Although, the domain gaps between unpaired nighttime infrared and daytime visible videos are even huger than paired ones that captured at the same time, establishing an effective translat…
In this paper, we present an attribute-guided deep coupled learning framework to address the problem of matching polarimetric thermal face photos against a gallery of visible faces. The coupled framework contains two sub-networks, one dedicated to the visible spectrum and the second sub-network dedicated to the polarimetric thermal spectrum. Each sub-network is made of a generative adversarial network (GAN) architecture. We propose a novel Attribute-Guided Coupled Generative Adversarial Network (AGC-GAN) architecture which utilizes facial attributes to improve the thermal-to-visible face recog…
Johns Hopkins University（约翰斯·霍普金斯大学）；DEVCOM Army Research Laboratory（美国陆军作战能力发展司令部陆军研究实验室）
Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution. This is unlikely in real-world long-range surveillance systems, since humans are distant from the cameras. To address this issue, we introduce the task of thermal-to-visible face verification from low-resolution thermal images. Furthermore, we propose Axial-Generative Adversarial Network (Axial-GAN) to synthesize high-resolution visible images for matching. In the proposed approach we augment the GAN framework with axial-attention layers which leverage the recent adv…
Modern-day surveillance systems perform person recognition using deep learning-based face verification networks. Most state-of-the-art facial verification systems are trained using visible spectrum images. But, acquiring images in the visible spectrum is impractical in scenarios of low-light and nighttime conditions, and often images are captured in an alternate domain such as the thermal infrared domain. Facial verification in thermal images is often performed after retrieving the corresponding visible domain images. This is a well-established problem often known as the Thermal-to-Visible (T2…
In many practical applications of long-range imaging such as biometrics and surveillance, thermal imagining modalities are often used to capture images in low-light and nighttime conditions. However, such imaging systems often suffer from atmospheric turbulence, which introduces severe blur and deformation artifacts to the captured images. Such an issue is unavoidable in long-range imaging and significantly decreases the face verification accuracy. In this paper, we first investigate the problem with a turbulence simulation method on real-world thermal images. An end-to-end reconstruction meth…
Whiting School of Engineering, Johns Hopkins University（约翰斯·霍普金斯大学怀廷工程学院）
Synthesis of face images from visual attributes is an important problem in computer vision and biometrics due to its applications in law enforcement and entertainment. Recent advances in deep generative networks have made it possible to synthesize high-quality face images from visual attributes. However, existing methods are specifically designed for generating unimodal images (i.e visible faces) from attributes. In this paper, we propose a novel generative adversarial network that simultaneously synthesizes identity preserving multimodal face images (i.e. visible, sketch, thermal, etc.) from …
Impact of Iris Pigmentation on Performance Bias in Visible Iris Verification Systems: A Comparative Study
Indian Institute of Technology Mandi（印度曼迪理工学院）；Technology Innovation Hub, Indian Institute of Technology Mandi（印度曼迪理工学院技术创新中心）；Norwegian University of Science and Technology (NTNU)（挪威科技大学）
State-of-the-art methods of attribute detection from faces almost always assume the presence of a full, unoccluded face. Hence, their performance degrades for partially visible and occluded faces. In this paper, we introduce SPLITFACE, a deep convolutional neural network-based method that is explicitly designed to perform attribute detection in partially occluded faces. Taking several facial segments and the full face as input, the proposed method takes a data driven approach to determine which attributes are localized in which facial segments. The unique architecture of the network allows eac…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland, College Park（马里兰大学学院公园分校）
Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears to contribute to bias in face recognition. However, existing bias mitigation approaches generally require end-to-end training and are unable to achieve high verification accuracy. Therefore, we present a descriptor-based adversarial de-biasing approach called `Protected Attribute Suppression System (PASS)'. PASS can be trained on top of descriptors obtained…
U.S. Army Research Laboratory（美国陆军研究实验室）；Booz Allen Hamilton（博思艾伦汉密尔顿）
Synthesis of visible spectrum faces from thermal facial imagery is a promising approach for heterogeneous face recognition; enabling existing face recognition software trained on visible imagery to be leveraged, and allowing human analysts to verify cross-spectrum matches more effectively. We propose a new synthesis method to enhance the discriminative quality of synthesized visible face imagery by leveraging both global (e.g., entire face) and local regions (e.g., eyes, nose, and mouth). Here, each region provides (1) an independent representation for the corresponding area, and (2) additiona…
In this paper, we present a deep coupled framework to address the problem of matching sketch image against a gallery of mugshots. Face sketches have the essential in- formation about the spatial topology and geometric details of faces while missing some important facial attributes such as ethnicity, hair, eye, and skin color. We propose a cou- pled deep neural network architecture which utilizes facial attributes in order to improve the sketch-photo recognition performance. The proposed Attribute-Assisted Deep Con- volutional Neural Network (AADCNN) method exploits the facial attributes and le…
MSGFusion: Multimodal Scene Graph-Guided Infrared and Visible Image Fusion
College of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）；College of Electronic Engineering, Ocean University of China（中国海洋大学电子工程学院）
Attributes, or semantic features, have gained popularity in the past few years in domains ranging from activity recognition in video to face verification. Improving the accuracy of attribute classifiers is an important first step in any application which uses these attributes. In most works to date, attributes have been considered to be independent. However, we know this not to be the case. Many attributes are very strongly related, such as heavy makeup and wearing lipstick. We propose to take advantage of attribute relationships in three ways: by using a multi-task deep convolutional neural n…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）；Michigan State University（密歇根州立大学）
Impact due to demographic factors such as age, sex, race, etc., has been studied extensively in automated face recognition systems. However, the impact of \textit{digitally modified} demographic and facial attributes on face recognition is relatively under-explored. In this work, we study the effect of attribute manipulations induced via generative adversarial networks (GANs) on face recognition performance. We conduct experiments on the CelebA dataset by intentionally modifying thirteen attributes using AttGAN and STGAN and evaluating their impact on two deep learning-based face verification …
The Chinese University of Hong Kong（香港中文大学）；SenseTime Group Limited（商汤集团有限公司）；Peking University（北京大学）
This paper proposes learning disentangled but complementary face features with minimal supervision by face identification. Specifically, we construct an identity Distilling and Dispelling Autoencoder (D2AE) framework that adversarially learns the identity-distilled features for identity verification and the identity-dispelled features to fool the verification system. Thanks to the design of two-stream cues, the learned disentangled features represent not only the identity or attribute but the complete input image. Comprehensive evaluations further demonstrate that the proposed features not onl…
Rutgers, The State University of New Jersey（罗格斯大学新泽西州立大学）；U.S. Army Research Laboratory（美国陆军研究实验室）；Booz Allen Hamilton（博思艾伦汉密尔顿公司）；Johns Hopkins University（约翰斯·霍普金斯大学）
The large domain discrepancy between faces captured in polarimetric (or conventional) thermal and visible domain makes cross-domain face verification a highly challenging problem for human examiners as well as computer vision algorithms. Previous approaches utilize either a two-step procedure (visible feature estimation and visible image reconstruction) or an input-level fusion technique, where different Stokes images are concatenated and used as a multi-channel input to synthesize the visible image given the corresponding polarimetric signatures. Although these methods have yielded improvemen…
In action understanding in indoor, we have to recognize human pose and action considering privacy. Although camera images can be used for highly accurate human action recognition, camera images do not preserve privacy. Therefore, we propose a new task for human instance segmentation from invisible information, especially airborne ultrasound, for action recognition. To perform instance segmentation from invisible information, we first convert sound waves to reflected sound directional images (sound images). Although the sound images can roughly identify the location of a person, the detailed sh…
Centre de Développement des Technologies Avancées（先进技术发展中心）；University of Oulu（奥卢大学）；Ecole Nationale Supèrieure d’Informatique（国立高等信息学学院）；Northwestern Polytechnical University（西北工业大学）
Automatic kinship verification using facial images is a relatively new and challenging research problem in computer vision. It consists in automatically predicting whether two persons have a biological kin relation by examining their facial attributes. While most of the existing works extract shallow handcrafted features from still face images, we approach this problem from spatio-temporal point of view and explore the use of both shallow texture features and deep features for characterizing faces. Promising results, especially those of deep features, are obtained on the benchmark UvA-NEMO Smi…
Obtaining compact and discriminative features is one of the major challenges in many of the real-world image classification tasks such as face verification and object recognition. One possible approach is to represent input image on the basis of high-level features that carry semantic meaning which humans can understand. In this paper, a model coined deep attribute network (DAN) is proposed to address this issue. For an input image, the model outputs the attributes of the input image without performing any classification. The efficacy of the proposed model is evaluated on unconstrained face ve…
University of Notre Dame（Notre Dame 大学）；Indiana University South Bend（印第安纳大学南本德分校）；University of North Carolina Wilmington（北卡罗来纳大学 Wilmington 分校）；Florida Institute of Technology（佛罗里达理工学院）
MTVDiff: Multimodal Conditional Latent Diffusion for Enhanced Thermal-to-Visible Face Translation
School of Computer Science and Engineering, Southeast University（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)（新一代人工智能技术及其交叉应用重点实验室（东南大学））；Monash University（莫纳什大学）
University of Houston（休斯顿大学）；National Center of Scientific Research Demokritos（德谟克利特国家科学研究中心）；University of Ioannina（约阿尼纳大学）
Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped after performing hierarchical clustering based on their correlation. The clusters of tasks are learned in a curriculum learning setup by transferring knowledge between…
Fraunhofer ITWM（弗劳恩霍夫工业数学研究所）；IWR, University of Heidelberg（海德堡大学科学计算跨学科中心）；Manchester Metropolitan University（曼彻斯特城市大学）；IMLA, Offenburg University（奥芬堡大学机器学习与分析研究所）
Facial image manipulation is a generation task where the output face is shifted towards an intended target direction in terms of facial attribute and styles. Recent works have achieved great success in various editing techniques such as style transfer and attribute translation. However, current approaches are either focusing on pure style transfer, or on the translation of predefined sets of attributes with restricted interactivity. To address this issue, we propose FacialGAN, a novel framework enabling simultaneous rich style transfers and interactive facial attributes manipulation. While pre…
Most current multi-object trackers focus on short-term tracking, and are based on deep and complex systems that often cannot operate in real-time, making them impractical for video-surveillance. In this paper we present a long-term, multi-face tracking architecture conceived for working in crowded contexts where faces are often the only visible part of a person. Our system benefits from advances in the fields of face detection and face recognition to achieve long-term tracking, and is particularly unconstrained to the motion and occlusions of people. It follows a tracking-by-detection approach…
Deep Learning systems need large data for training. Datasets for training face verification systems are difficult to obtain and prone to privacy issues. Synthetic data generated by generative models such as GANs can be a good alternative. However, we show that data generated from GANs are prone to bias and fairness issues. Specifically, GANs trained on FFHQ dataset show biased behavior towards generating white faces in the age group of 20-29. We also demonstrate that synthetic faces cause disparate impact, specifically for race attribute, when used for fine tuning face verification systems.
GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT
Zhejiang Key Laboratory of Space Information Sensing and Transmission（浙江空间信息感知与传输重点实验室）；Hangzhou Dianzi University（杭州电子科技大学）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；Children's Hospital, Zhejiang University School of Medicine（浙江大学医学院附属儿童医院）
The Open Images Dataset contains approximately 9 million images and is a widely accepted dataset for computer vision research. As is common practice for large datasets, the annotations are not exhaustive, with bounding boxes and attribute labels for only a subset of the classes in each image. In this paper, we present a new set of annotations on a subset of the Open Images dataset called the MIAP (More Inclusive Annotations for People) subset, containing bounding boxes and attributes for all of the people visible in those images. The attributes and labeling methodology for the MIAP subset were…
McGill University（麦吉尔大学）；Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）
Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionately and negatively impact minority groups, particularly when used by law enforcement. The majority of bias reduction methods have several drawbacks: they use an end-to-end retraining approach, may not be feasible due to privacy issues, and often reduce accuracy. An alternative approach is post-processing methods that build fairer decision classifier…
Beijing University of Posts and Telecommunications（北京邮电大学）
Labeled Faces in the Wild (LFW) database has been widely utilized as the benchmark of unconstrained face verification and due to big data driven machine learning methods, the performance on the database approaches nearly 100%. However, we argue that this accuracy may be too optimistic because of some limiting factors. Besides different poses, illuminations, occlusions and expressions, cross-age face is another challenge in face recognition. Different ages of the same person result in large intra-class variations and aging process is unavoidable in real world face verification. However, LFW doe…
Color images are easy to understand visually and can acquire a great deal of information, such as color and texture. They are highly and widely used in tasks such as segmentation. On the other hand, in indoor person segmentation, it is necessary to collect person data considering privacy. We propose a new task for human segmentation from invisible information, especially airborne ultrasound. We first convert ultrasound waves to reflected ultrasound directional images (ultrasound images) to perform segmentation from invisible information. Although ultrasound images can roughly identify a person…
Recent work reports disparate performance for intersectional racial groups across face recognition tasks: face verification and identification. However, the definition of those racial groups has a significant impact on the underlying findings of such racial bias analysis. Previous studies define these groups based on either demographic information (e.g. African, Asian etc.) or skin tone (e.g. lighter or darker skins). The use of such sensitive or broad group definitions has disadvantages for bias investigation and subsequent counter-bias solutions design. By contrast, this study introduces an …
The Hong Kong University of Science and Technology（香港科技大学）；Tencent Youtu（腾讯优图）
We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the CycleGAN and propose conditional CycleGAN, which is designed to 1) handle unpaired training data because the training low/high-res and high-res attribute images may not necessarily align with each other, and to 2) allow easy control of the appearance of the generated face via the…
Huazhong University of Science and Technology（华中科技大学）；Zagazig University（扎加齐格大学）
Face recognition is known to be vulnerable to adversarial face images. Existing works craft face adversarial images by indiscriminately changing a single attribute without being aware of the intrinsic attributes of the images. To this end, we propose a new Semantic Adversarial Attack called SAA-StarGAN that tampers with the significant facial attributes for each image. We predict the most significant attributes by applying the cosine similarity or probability score. The probability score method is based on training a Face Verification model for an attribute prediction task to obtain a class pr…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Heterogeneous Face Recognition (HFR) aims to match faces across different domains (e.g., visible to near-infrared images), which has been widely applied in authentication and forensics scenarios. However, HFR is a challenging problem because of the large cross-domain discrepancy, limited heterogeneous data pairs, and large variation of facial attributes. To address these challenges, we propose a new HFR method from the perspective of heterogeneous data augmentation, named Face Synthesis with Identity-Attribute Disentanglement (FSIAD). Firstly, the identity-attribute disentanglement (IAD) decou…
