Advances in Computer Vision and Pattern Recognition

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains. 
 
The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation and stochastic gradient descent, and can thus be implemented with little effort using any of the deep learning packages. 
 
We demonstrate the success of our approach for two distinct classification problems (document sentiment analysis and image classification), where state-of-the-art domain adaptation performance on standard benchmarks is achieved. We also validate the approach for descriptor learning task in the context of person re-identification application.

Yaroslav Ganin

Evgeniya Ustinova

Hana Ajakan

Pascal Germain

Hugo Larochelle

François Laviolette

Mario Marchand

Victor Lempitsky

Domain-Adversarial Training of Neural Networks

神经网络的领域对抗训练

Christian Rathgeb

Andreas Uhl

Peter Wild

Heinz Hofbauer

Handbook of Iris Recognition

Design Decisions for an Iris Recognition SDK

虹膜识别SDK的设计决策

A. Ardeshir Goshtasby

Image Registration

Image Registration Methods

图像配准方法

Xiong Zhou

Saurabh Prasad

Hyperspectral Image Analysis

Advances in Deep Learning for Hyperspectral Image Analysis—Addressing Challenges Arising in Practical Imaging Scenarios

深度学习在高光谱图像分析中的进展——解决实际成像场景中的挑战

Jascha Kolberg

Marta Gomez-Barrero

Sushma Venkatesh

Raghavendra Ramachandra

Christoph Busch

Handbook of Vascular Biometrics

Presentation Attack Detection for Finger Recognition

指纹识别中的呈现攻击检测

Recent years have witnessed exciting progress in automatic face swapping and editing. Many techniques have been proposed, facilitating the rapid development of creative content creation. The emergence and easy accessibility of such techniques, however, also cause potential unprecedented ethical and moral issues. To this end, academia and industry proposed several effective forgery detection methods. Nonetheless, challenges could still exist. (1) Current face manipulation advances can produce high-fidelity fake videos, rendering forgery detection challenging. (2) The generalization capability of most existing detection models is poor, particularly in real-world scenarios where the media sources and distortions are unknown. The primary difficulty in overcoming these challenges is the lack of amenable datasets for real-world face forgery detection. Most existing datasets are either of a small number, of low quality, or overly artificial. Meanwhile, the large distribution gap between training data and actual test videos also leads to weak generalization ability. In this chapter, we present our on-going effort of constructing DeeperForensics-1.0, a large-scale forgery detection dataset, to address the challenges above. We discuss approaches to ensure the quality and diversity of the dataset. Besides, we describe the observations we obtained from organizing DeeperForensics Challenge 2020, a real-world face forgery detection competition based on DeeperForensics-1.0. Specifically, we summarize the winning solutions and provide some discussions on potential research directions.

Liming Jiang

Wayne Wu

Chen Qian

Chen Change Loy

Handbook of Digital Face Manipulation and Detection

DeepFakes Detection: the DeeperForensics Dataset and Challenge

DeepFakes检测：DeeperForensics数据集与挑战

Face recognition in controlled environments is nowadays considered rather reliable, and very good accuracy levels can be achieved by state-of-the-art systems in controlled scenarios. However, even under these desirable conditions, digital image alterations can severely affect the recognition performance. In particular, several studies show that automatic face recognition systems are very sensitive to the so-called face morphing attack, where face images of two individuals are mixed to produce a new face image containing facial features of both subjects. Face morphing represents nowadays a big security threat particularly in the context of electronic identity documentsbecause it can be successfully exploited for criminal intents, for instance to fool Automated Border Control (ABC) systems thus overcoming security controls at the borders. This chapter will describe the face morphing process, in an overview ranging from the traditional techniques based on geometry warping and texture blending to the most recent and innovative approaches based on deep neural networks. Moreover, the sensitivity of state-of-the-art face recognition algorithms to the face morphing attack will be assessed using morphed images of different quality generated using various morphing methods to identify possible factors influencing the probability of success of the attack.

Matteo Ferrara

Annalisa Franco

Morph Creation and Vulnerability of Face Recognition Systems to Morphing

人脸融合生成及其对人脸识别系统的脆弱性

Biometric technologies, in particular facerecognition, are employed in many personal, commercial, and governmental identity management systems around the world. The processing of digitally manipulated face images within a face recognition system may lead to false decisions and thus decrease the reliability of the decision system. This necessitates the development of manipulation detection modules which can be seamlessly integrated into the processing chain of face recognition systems. This chapter discusses the impact of face image manipulation on face recognition technologies. To this end, the basic processes and key components of biometric systems are briefly introduced with particular emphasis on facial recognition. Additionally, face manipulation detection scenarios and concepts of how to integrate detection methods to face recognition systems are discussed. In an experimental evaluation, it is shown that different types of face manipulation, i.e. retouching, face morphing, and swapping, can significantly affect the biometric performance of face recognition systems and hence impair their security. Eventually, this chapter provides an outlook on issues and challenges that face manipulation poses to face recognition technologies.

Mathias Ibsen

Daniel Fischer

Pawel Drozdowski

Digital Face Manipulation in Biometric Systems

生物识别系统中的数字人脸篡改

In recent years there have been astonishing advances in AI-based synthetic media generation. Thanks to deep learning methods it is now possible to generate visual data with a high level of realism. This is especially true for human faces. Advanced deep learning tools allow one to easily change some specific attributes of a real face or even create brand new identities. Although this opens up a large number of new opportunities, just think of the entertainment industry, it also undermines the trustworthiness of media content and supports the spread of fake identities over the internet. In this context, there is a fundamental need to develop robust and automatic tools capable of distinguishing synthetic faces from real ones. The scientific community is making a huge research effort in this field, proposing several interesting approaches. However, a universal detector is yet to come. Fundamentally, the research in this field is like a cat and mouse game, with new detectors that are designed to deal with powerful synthetic face generators, while the latter keep improving to produce more and more realistic images. In this chapter we will present the most effective techniques proposed in the literature for the detection of synthetic faces. We will analyze their rationale, present real-world application scenarios , and compare different approaches in terms of accuracy and generalization ability.

出版信息	出版商: Springer Science and Business Media Deutschland GmbH，出版周期: ，期刊类型: book-series，开源期刊: 否
基本数据	创刊年份: 2014，原创研究文献占比: ，自引率:， Gold OA占比:

Advances in Computer Vision and Pattern Recognition

期刊引文格式

有 1 位以上作者的期刊

有 2 位作者的期刊

有 3 位作者的期刊

有 5 位以上作者的期刊

书籍引用格式

学位论文引用格式

网页引用格式

专利引用格式

手工熬夜修改参考文献？研飞自动匹配期刊，一键轻松成稿，支持 Word/WPS

投稿经验分享

Domain-Adversarial Training of Neural Networks

Design Decisions for an Iris Recognition SDK

Image Registration Methods

Advances in Deep Learning for Hyperspectral Image Analysis—Addressing Challenges Arising in Practical Imaging Scenarios

Presentation Attack Detection for Finger Recognition

DeepFakes Detection: the DeeperForensics Dataset and Challenge

Morph Creation and Vulnerability of Face Recognition Systems to Morphing

Digital Face Manipulation in Biometric Systems

Detection of AI-Generated Synthetic Faces

Deblurring Face Images Using Deep Networks