Chang-Tsun Li

Bosheng Yan, Chang-Tsun Li, Xuequan Lu

Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising performance in the intra-dataset evaluation setting (i.e., training and testing on the same dataset), but are unable to perform satisfactorily in the inter-dataset evaluation setting (i.e., training on one dataset and testing on another). Most of the previous methods use the backbone network to extract global features for making predictions and only employ binary supervision (i.e., indicating whether the training instances are fake or authentic) to train the network. Classification merely based on the learning of global features leads often leads to weak generalizability to unseen manipulation methods. In addition, the reconstruction task can improve the learned representations. In this paper, we introduce a novel approach for deepfake detection, which considers the reconstruction and classification tasks simultaneously to address these problems. This method shares the information learned by one task with the other, which focuses on a different aspect other existing works rarely consider and hence boosts the overall performance. In particular, we design a two-branch Convolutional AutoEncoder (CAE), in which the Convolutional Encoder used to compress the feature map into the latent representation is shared by both branches. Then the latent representation of the input data is fed to a simple classifier and the unsupervised reconstruction component simultaneously. Our network is trained end-to-end. Experiments demonstrate that our method achieves state-of-the-art performance on three commonly-used datasets, particularly in the cross-dataset evaluation setting.

Chenhao Xu, Chang-Tsun Li, Yongjian Hu et al.

Video instance segmentation, also known as multi-object tracking and segmentation, is an emerging computer vision research area introduced in 2019, aiming at detecting, segmenting, and tracking instances in videos simultaneously. By tackling the video instance segmentation tasks through effective analysis and utilization of visual information in videos, a range of computer vision-enabled applications (e.g., human action recognition, medical image processing, autonomous vehicle navigation, surveillance, etc) can be implemented. As deep-learning techniques take a dominant role in various computer vision areas, a plethora of deep-learning-based video instance segmentation schemes have been proposed. This survey offers a multifaceted view of deep-learning schemes for video instance segmentation, covering various architectural paradigms, along with comparisons of functional performance, model complexity, and computational overheads. In addition to the common architectural designs, auxiliary techniques for improving the performance of deep-learning models for video instance segmentation are compiled and discussed. Finally, we discuss a range of major challenges and directions for further investigations to help advance this promising research field.

Chenhao Xu, Chang-Tsun Li, Chee Peng Lim et al.

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to devices with limited computing resources. To mitigate the aforementioned challenges, this paper introduces a novel horizontally scalable vision transformer (HSViT) scheme. Specifically, a novel image-level feature embedding is introduced to ViT, where the preserved inductive bias allows the model to eliminate the need for pre-training while outperforming on small datasets. Besides, a novel horizontally scalable architecture is designed, facilitating collaborative model training and inference across multiple computing devices. The experimental results depict that, without pre-training, HSViT achieves up to 10% higher top-1 accuracy than state-of-the-art schemes on small datasets, while providing existing CNN backbones up to 3.1% improvement in top-1 accuracy on ImageNet. The code is available at https://github.com/xuchenhao001/HSViT.

Yijun Quan, Chang-Tsun Li, Yujue Zhou et al.

Device fingerprints like sensor pattern noise (SPN) are widely used for provenance analysis and image authentication. Over the past few years, the rapid advancement in digital photography has greatly reshaped the pipeline of image capturing process on consumer-level mobile devices. The flexibility of camera parameter settings and the emergence of multi-frame photography algorithms, especially high dynamic range (HDR) imaging, bring new challenges to device fingerprinting. The subsequent study on these topics requires a new purposefully built image dataset. In this paper, we present the Warwick Image Forensics Dataset, an image dataset of more than 58,600 images captured using 14 digital cameras with various exposure settings. Special attention to the exposure settings allows the images to be adopted by different multi-frame computational photography algorithms and for subsequent device fingerprinting. The dataset is released as an open-source, free for use for the digital forensic community.

Haoyi Wang, Victor Sanchez, Chang-Tsun Li

Cross-age facial images are typically challenging and expensive to collect, making noise-free age-oriented datasets relatively small compared to widely-used large-scale facial datasets. Additionally, in real scenarios, images of the same subject at different ages are usually hard or even impossible to obtain. Both of these factors lead to a lack of supervised data, which limits the versatility of supervised methods for age-invariant face recognition, a critical task in applications such as security and biometrics. To address this issue, we propose a novel semi-supervised learning approach named Cross-Age Contrastive Learning (CACon). Thanks to the identity-preserving power of recent face synthesis models, CACon introduces a new contrastive learning method that leverages an additional synthesized sample from the input image. We also propose a new loss function in association with CACon to perform contrastive learning on a triplet of samples. We demonstrate that our method not only achieves state-of-the-art performance in homogeneous-dataset experiments on several age-invariant face recognition benchmarks but also outperforms other methods by a large margin in cross-dataset experiments.

Haoyi Wang, Victor Sanchez, Chang-Tsun Li et al.

Generalized age feature extraction is crucial for age-related facial analysis tasks, such as age estimation and age-invariant face recognition (AIFR). Despite the recent successes of models in homogeneous-dataset experiments, their performance drops significantly in cross-dataset evaluations. Most of these models fail to extract generalized age features as they only attempt to map extracted features with training age labels directly without explicitly modeling the natural ordinal progression of aging. In this paper, we propose Order-Enhanced Contrastive Learning (OrdCon), a novel contrastive learning framework designed explicitly for ordinal attributes like age. Specifically, to extract generalized features, OrdCon aligns the direction vector of two features with either the natural aging direction or its reverse to model the ordinal process of aging. To further enhance generalizability, OrdCon leverages a novel soft proxy matching loss as a second contrastive objective, ensuring that features are positioned around the center of each age cluster with minimal intra-class variance and proportionally away from other clusters. By modeling the ageing process, the framework can enhance generalizability by improving the alignment of samples from the same class and reducing the divergence of direction vectors. We demonstrate that our proposed method achieves comparable results to state-of-the-art methods on various benchmark datasets in homogeneous-dataset evaluations for both age estimation and AIFR. In cross-dataset experiments, OrdCon outperforms other methods by reducing the mean absolute error by approximately 1.38 on average for the age estimation task and boosts the average accuracy for AIFR by 1.87%.

Xufeng Lin, Chang-Tsun Li, Scott Adams et al.

As an essential prerequisite task in image-based plant phenotyping, leaf segmentation has garnered increasing attention in recent years. While self-supervised learning is emerging as an effective alternative to various computer vision tasks, its adaptation for image-based plant phenotyping remains rather unexplored. In this work, we present a self-supervised leaf segmentation framework consisting of a self-supervised semantic segmentation model, a color-based leaf segmentation algorithm, and a self-supervised color correction model. The self-supervised semantic segmentation model groups the semantically similar pixels by iteratively referring to the self-contained information, allowing the pixels of the same semantic object to be jointly considered by the color-based leaf segmentation algorithm for identifying the leaf regions. Additionally, we propose to use a self-supervised color correction model for images taken under complex illumination conditions. Experimental results on datasets of different plant species demonstrate the potential of the proposed self-supervised framework in achieving effective and generalizable leaf segmentation.

Nan Sun, Chang-Tsun Li, Hin Chan et al.

Advances of emerging Information and Communications Technology (ICT) technologies push the boundaries of what is possible and open up new markets for innovative ICT products and services. The adoption of ICT products and systems with security properties depends on consumers' confidence and markets' trust in the security functionalities and whether the assurance measures applied to these products meet the inherent security requirements. Such confidence and trust are primarily gained through the rigorous development of security requirements, validation criteria, evaluation, and certification. Common Criteria for Information Technology Security Evaluation (often referred to as Common Criteria or CC) is an international standard (ISO/IEC 15408) for cyber security certification. In this paper, we conduct a systematic review of the CC standards and its adoptions. Adoption barriers of the CC are also investigated based on the analysis of current trends in security evaluation. Specifically, we share the experiences and lessons gained through the recent Development of Australian Cyber Criteria Assessment (DACCA) project that promotes the CC among stakeholders in ICT security products related to specification, development, evaluation, certification and approval, procurement, and deployment. Best practices on developing Protection Profiles, recommendations, and future directions for trusted cybersecurity advancement are presented.

Haoyi Wang, Victor Sanchez, Chang-Tsun Li

With the increasing popularity of convolutional neural networks (CNNs), recent works on face-based age estimation employ these networks as the backbone. However, state-of-the-art CNN-based methods treat each facial region equally, thus entirely ignoring the importance of some facial patches that may contain rich age-specific information. In this paper, we propose a face-based age estimation framework, called Attention-based Dynamic Patch Fusion (ADPF). In ADPF, two separate CNNs are implemented, namely the AttentionNet and the FusionNet. The AttentionNet dynamically locates and ranks age-specific patches by employing a novel Ranking-guided Multi-Head Hybrid Attention (RMHHA) mechanism. The FusionNet uses the discovered patches along with the facial image to predict the age of the subject. Since the proposed RMHHA mechanism ranks the discovered patches based on their importance, the length of the learning path of each patch in the FusionNet is proportional to the amount of information it carries (the longer, the more important). ADPF also introduces a novel diversity loss to guide the training of the AttentionNet and reduce the overlap among patches so that the diverse and important patches are discovered. Through extensive experiments, we show that our proposed framework outperforms state-of-the-art methods on several age estimation benchmark datasets.

Manisha, Chang-Tsun Li, Xufeng Lin et al.

Source camera identification tools assist image forensic investigators to associate an image in question with a suspect camera. Various techniques have been developed based on the analysis of the subtle traces left in the images during the acquisition. The Photo Response Non Uniformity (PRNU) noise pattern caused by sensor imperfections has been proven to be an effective way to identify the source camera. The existing literature suggests that the PRNU is the only fingerprint that is device-specific and capable of identifying the exact source device. However, the PRNU is susceptible to camera settings, image content, image processing operations, and counter-forensic attacks. A forensic investigator unaware of counter-forensic attacks or incidental image manipulations is at the risk of getting misled. The spatial synchronization requirement during the matching of two PRNUs also represents a major limitation of the PRNU. In recent years, deep learning based approaches have been successful in identifying source camera models. However, the identification of individual cameras of the same model through these data-driven approaches remains unsatisfactory. In this paper, we bring to light the existence of a new robust data-driven device-specific fingerprint in digital images which is capable of identifying the individual cameras of the same model. It is discovered that the new device fingerprint is location-independent, stochastic, and globally available, which resolve the spatial synchronization issue. Unlike the PRNU, which resides in the high-frequency band, the new device fingerprint is extracted from the low and mid-frequency bands, which resolves the fragility issue that the PRNU is unable to contend with. Our experiments on various datasets demonstrate that the new fingerprint is highly resilient to image manipulations such as rotation, gamma correction, and aggressive JPEG compression.

Xufeng Lin, Chang-Tsun Li, Victor Sanchez et al.

Driven by recent advances in object detection with deep neural networks, the tracking-by-detection paradigm has gained increasing prevalence in the research community of multi-object tracking (MOT). It has long been known that appearance information plays an essential role in the detection-to-track association, which lies at the core of the tracking-by-detection paradigm. While most existing works consider the appearance distances between the detections and the tracks, they ignore the statistical information implied by the historical appearance distance records in the tracks, which can be particularly useful when a detection has similar distances with two or more tracks. In this work, we propose a hybrid track association (HTA) algorithm that models the historical appearance distances of a track with an incremental Gaussian mixture model (IGMM) and incorporates the derived statistical information into the calculation of the detection-to-track association cost. Experimental results on three MOT benchmarks confirm that HTA effectively improves the target identification performance with a small compromise to the tracking speed. Additionally, compared to many state-of-the-art trackers, the DeepSORT tracker equipped with HTA achieves better or comparable performance in terms of the balance of tracking quality and speed.

Ching-Chun Chang, Xu Wang, Sisheng Chen et al.

Deep learning is regarded as a promising solution for reversible steganography. There is an accelerating trend of representing a reversible steo-system by monolithic neural networks, which bypass intermediate operations in traditional pipelines of reversible steganography. This end-to-end paradigm, however, suffers from imperfect reversibility. By contrast, the modular paradigm that incorporates neural networks into modules of traditional pipelines can stably guarantee reversibility with mathematical explainability. Prediction-error modulation is a well-established reversible steganography pipeline for digital images. It consists of a predictive analytics module and a reversible coding module. Given that reversibility is governed independently by the coding module, we narrow our focus to the incorporation of neural networks into the analytics module, which serves the purpose of predicting pixel intensities and a pivotal role in determining capacity and imperceptibility. The objective of this study is to evaluate the impacts of different training configurations upon predictive accuracy of neural networks and provide practical insights. In particular, we investigate how different initialisation strategies for input images may affect the learning process and how different training strategies for dual-layer prediction respond to the problem of distributional shift. Furthermore, we compare steganographic performance of various model architectures with different loss functions.

Sheldon Fung, Xuequan Lu, Chao Zhang et al.

Face deepfake detection has seen impressive results recently. Nearly all existing deep learning techniques for face deepfake detection are fully supervised and require labels during training. In this paper, we design a novel deepfake detection method via unsupervised contrastive learning. We first generate two different transformed versions of an image and feed them into two sequential sub-networks, i.e., an encoder and a projection head. The unsupervised training is achieved by maximizing the correspondence degree of the outputs of the projection head. To evaluate the detection performance of our unsupervised method, we further use the unsupervised features to train an efficient linear classification network. Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings. We also conduct ablation studies for our method.

Shan Lin, Chang-Tsun Li, Alex C. Kot

With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. However, these models trained on a single dataset usually suffer from considerable performance degradation when applied to videos of a different camera network. To make Person Re-ID systems more practical and scalable, several cross-dataset domain adaptation methods have been proposed, which achieve high performance without the labeled data from the target domain. However, these approaches still require the unlabeled data of the target domain during the training process, making them impractical. A practical Person Re-ID system pre-trained on other datasets should start running immediately after deployment on a new site without having to wait until sufficient images or videos are collected and the pre-trained model is tuned. To serve this purpose, in this paper, we reformulate person re-identification as a multi-dataset domain generalization problem. We propose a multi-dataset feature generalization network (MMFA-AAE), which is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to `unseen' camera systems. The network is based on an adversarial auto-encoder to learn a generalized domain-invariant latent feature representation with the Maximum Mean Discrepancy (MMD) measure to align the distributions across multiple domains. Extensive experiments demonstrate the effectiveness of the proposed method. Our MMFA-AAE approach not only outperforms most of the domain generalization Person Re-ID methods, but also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.

Haoyi Wang, Victor Sanchez, Chang-Tsun Li

The vanilla Generative Adversarial Networks (GAN) are commonly used to generate realistic images depicting aged and rejuvenated faces. However, the performance of such vanilla GANs in the age-oriented face synthesis task is often compromised by the mode collapse issue, which may result in the generation of faces with minimal variations and a poor synthesis accuracy. In addition, recent age-oriented face synthesis methods use the L1 or L2 constraint to preserve the identity information on synthesized faces, which implicitly limits the identity permanence capabilities when these constraints are associated with a trivial weighting factor. In this paper, we propose a method for the age-oriented face synthesis task that achieves a high synthesis accuracy with strong identity permanence capabilities. Specifically, to achieve a high synthesis accuracy, our method tackles the mode collapse issue with a novel Conditional Discriminator Pool (CDP), which consists of multiple discriminators, each targeting one particular age category. To achieve strong identity permanence capabilities, our method uses a novel Adversarial Triplet loss. This loss, which is based on the Triplet loss, adds a ranking operation to further pull the positive embedding towards the anchor embedding resulting in significantly reduced intra-class variances in the feature space. Through extensive experiments, we show that our proposed method outperforms state-of-the-art methods in terms of synthesis accuracy and identity permanence capabilities, qualitatively and quantitatively.

Yijun Quan, Chang-Tsun Li

Photo Response Non-Uniformity (PRNU) has been used as a powerful device fingerprint for image forgery detection because image forgeries can be revealed by finding the absence of the PRNU in the manipulated areas. The correlation between an image's noise residual with the device's reference PRNU is often compared with a decision threshold to check the existence of the PRNU. A PRNU correlation predictor is usually used to determine this decision threshold assuming the correlation is content-dependent. However, we found that not only the correlation is content-dependent, but it also depends on the camera sensitivity setting. \textit{Camera sensitivity}, commonly known by the name of \textit{ISO speed}, is an important attribute in digital photography. In this work, we will show the PRNU correlation's dependency on ISO speed. Due to such dependency, we postulate that a correlation predictor is ISO speed-specific, i.e. \textit{reliable correlation predictions can only be made when a correlation predictor is trained with images of similar ISO speeds to the image in question}. We report the experiments we conducted to validate the postulate. It is realized that in the real-world, information about the ISO speed may not be available in the metadata to facilitate the implementation of our postulate in the correlation prediction process. We hence propose a method called Content-based Inference of ISO Speeds (CINFISOS) to infer the ISO speed from the image content.

Gary Storey, Ahmed Bouridane, Richard Jiang et al.

While facial biometrics has been widely used for identification purpose, it has recently been researched as medical biometrics for a range of diseases. In this chapter, we investigate the facial landmark detection for atypical 3D facial modelling in facial palsy cases, while potentially such modelling can assist the medical diagnosis using atypical facial features. In our work, a study of landmarks localisation methods such as stacked hourglass networks is conducted and evaluated to ascertain their accuracy when presented with unseen atypical faces. The evaluation highlights that the state-of-the-art stacked hourglass architecture outperforms other traditional methods.

Gary Storey, Richard Jiang, Shelagh Keogh et al.

The capability to perform facial analysis from video sequences has significant potential to positively impact in many areas of life. One such area relates to the medical domain to specifically aid in the diagnosis and rehabilitation of patients with facial palsy. With this application in mind, this paper presents an end-to-end framework, named 3DPalsyNet, for the tasks of mouth motion recognition and facial palsy grading. 3DPalsyNet utilizes a 3D CNN architecture with a ResNet backbone for the prediction of these dynamic tasks. Leveraging transfer learning from a 3D CNNs pre-trained on the Kinetics data set for general action recognition, the model is modified to apply joint supervised learning using center and softmax loss concepts. 3DPalsyNet is evaluated on a test set consisting of individuals with varying ranges of facial palsy and mouth motions and the results have shown an attractive level of classification accuracy in these task of 82% and 86% respectively. The frame duration and the loss function affect was studied in terms of the predictive qualities of the proposed 3DPalsyNet, where it was found shorter frame duration's of 8 performed best for this specific task. Centre loss and softmax have shown improvements in spatio-temporal feature learning than softmax loss alone, this is in agreement with earlier work involving the spatial domain.

Yihan Guo, Shan Lin, Xiao Ma et al.

Most existing real estate appraisal methods focus on building accuracy and reliable models from a given dataset but pay little attention to the extensibility of their trained model. As different cities usually contain a different set of location features (district names, apartment names), most existing mass appraisal methods have to train a new model from scratch for different cities or regions. As a result, these approaches require massive data collection for each city and the total training time for a multi-city property appraisal system will be extremely long. Besides, some small cities may not have enough data for training a robust appraisal model. To overcome these limitations, we develop a novel Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning (HFT+HLF) cross-city property appraisal framework. By transferring partial neural network learning from a source city and fine-tuning on the small amount of location information of a target city, our semi-supervised model can achieve similar or even superior performance compared to a fully supervised Artificial neural network (ANN) method.

Haoyi Wang, Xingjie Wei, Victor Sanchez et al.

Convolutional Neural Networks (CNN) have been applied to age-related research as the core framework. Although faces are composed of numerous facial attributes, most works with CNNs still consider a face as a typical object and do not pay enough attention to facial regions that carry age-specific feature for this particular task. In this paper, we propose a novel CNN architecture called Fusion Network (FusionNet) to tackle the age estimation problem. Apart from the whole face image, the FusionNet successively takes several age-specific facial patches as part of the input to emphasize the age-specific features. Through experiments, we show that the FusionNet significantly outperforms other state-of-the-art models on the MORPH II benchmark.

Shan Lin, Haoliang Li, Chang-Tsun Li et al.

Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. Such a setting severely limits their scalability in real-world applications where no labelled samples are available during the training phase. To overcome this limitation, we develop a novel unsupervised Multi-task Mid-level Feature Alignment (MMFA) network for the unsupervised cross-dataset person re-identification task. Under the assumption that the source and target datasets share the same set of mid-level semantic attributes, our proposed model can be jointly optimised under the person's identity classification and the attribute learning task with a cross-dataset mid-level feature alignment regularisation term. In this way, the learned feature representation can be better generalised from one dataset to another which further improve the person re-identification accuracy. Experimental results on four benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art baselines.