Author name cluster

Gerald Schaefer

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

EAAI Journal 2026 Journal Article

A gated recurrent unit-based soft actor–critic approach with social force model crowd simulation for improved mobile robot path planning

Dezhen Zhang
Guoxu Wang
Gerald Schaefer
Hui Fang
Junming Su

Mobile robot path planning is an essential function for many current and emerging applications of service robots. Despite consistent progress, learning a generalisable path planning model in a dynamic multiple-pedestrian environment is still a challenging task. In this paper, we construct a dynamic simulation environment based on a social force model to narrow the gap between simulation and reality so as to yield better generalisability for a path planning model. Using this simulation, we design a gated recurrent unit (GRU)-based soft actor–critic (SAC) neural network model which exploits future state predictions to reduce the exploration space in order to improve training convergence. Learning from scenarios driven by the social force model, we include GRU temporal predictions of pedestrian movements as an additional state feature to prevent the model from exploring less frequent or inactive behaviour patterns. Compared to other state-of-the-art offline reinforcement learning approaches, our experimental results show that GRU-SAC achieves faster convergence, yields improved collision avoidance, and obtains planned paths that are shorter and smoother. In addition, results from real-world corridor experiments demonstrate that agents trained with the social force model can better capture the emergent dynamic behaviours of pedestrians in high-density environments. This indicates that the proposed GRU-SAC model exhibits superior adaptability in complex scenarios and confirms its practical applicability in real-world settings.

Details DOI

AAAI Conference 2026 Conference Paper

ACID-Style: An Adaptive Condition Injection Diffusion Model for Arbitrary Style Transfer

Ting Yang
Siyu Yang
Xiyao Liu
Songtao Wu
Gerald Schaefer
Kuanhong Xu
Hui Fang

Arbitrary style transfer (AST), a popular AI-powered photo editing function, aims to strike an optimal balance between content and style injection from two images in order to generate a novel high-fidelity stylised image. Recently, diffusion models have been applied to AST due to their high generation quality as well as flexibility to embed conditions. However, these models are still not satisfactory and may exhibit inferior performance compared to non-diffusion based methods. This is due to the diffusion process not being purposely designed for AST, leading to suboptimal solutions to trade-off content preservation and style embedding. In this paper, we propose ACID-Style, a novel adaptive condition injection diffusion-based AST framework for improved content/style feature injection to address this research challenge. Using two lightweight adapters, a content and a style injection module, and an adaptive injection mechanism, our approach is able to fully exploit a pre-trained stable diffusion model for AST-specific adaptation and our diffusion model thus learns the most effective timing for content and style injection in the diffusion sampling process. Comprehensive evaluations demonstrate that our method achieves superior style transfer performance, both quantitatively and qualitatively, compared to other state-of-the-art style transfer methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Recoverable Facial Identity Protection via Adaptive Makeup Transfer Adversarial Attacks

Xiyao Liu
Junxing Ma
Xinda Wang
Qianyu Lin
Jian Zhang
Gerald Schaefer
Cagatay Turkay
Hui Fang

Unauthorised face recognition (FR) systems have posed significant threats to digital identity and privacy protection. To alleviate the risk of compromised identities, recent makeup transfer-based attack methods embed adversarial signals in order to confuse unauthorised FR systems. However, their major weakness is that they set up a fixed image unrelated to both the protected and the makeup reference images as the confusion identity, which in turn has a negative impact on both attack success rate and visual quality of transferred photos. In addition, the generated images cannot be recognised by authorised FR systems once attacks are triggered. To address these challenges, in this paper, we propose a Recoverable Makeup Transferred Generative Adversarial Network (RMT-GAN) which has the distinctive feature of improving its image-transfer quality by selecting a suitable transfer reference photo as the target identity. Moreover, our method offers a solution to recover the protected photos to their original counterparts that can be recognised by authorised systems. Experimental results demonstrate that our method provides significantly improved attack success rates while maintaining higher visual quality compared to state-of-the-art makeup transfer-based adversarial attack methods. Our code and supplementary materials are available on Github.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Gradient-Based Graph Attention for Scene Text Image Super-resolution

Xiangyuan Zhu
Kehua Guo
Hui Fang
Rui Ding
Zheng Wu
Gerald Schaefer

Scene text image super-resolution (STISR) in the wild has been shown to be beneficial to support improved vision-based text recognition from low-resolution imagery. An intuitive way to enhance STISR performance is to explore the well-structured and repetitive layout characteristics of text and exploit these as prior knowledge to guide model convergence. In this paper, we propose a novel gradient-based graph attention method to embed patch-wise text layout contexts into image feature representations for high-resolution text image reconstruction in an implicit and elegant manner. We introduce a non-local group-wise attention module to extract text features which are then enhanced by a cascaded channel attention module and a novel gradient-based graph attention module in order to obtain more effective representations by exploring correlations of regional and local patch-wise text layout properties. Extensive experiments on the benchmark TextZoom dataset convincingly demonstrate that our method supports excellent text recognition and outperforms the current state-of-the-art in STISR. The source code is available at https://github.com/xyzhu1/TSAN.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Robust Steganography without Embedding Based on Secure Container Synthesis and Iterative Message Recovery

Ziping Ma
Yuesheng Zhu
Guibo Luo
Xiyao Liu
Gerald Schaefer
Hui Fang

Synthesis-based steganography without embedding (SWE) methods transform secret messages to container images synthesised by generative networks, which eliminates distortions of container images and thus can fundamentally resist typical steganalysis tools. However, existing methods suffer from weak message recovery robustness, synthesis fidelity, and the risk of message leakage. To address these problems, we propose a novel robust steganography without embedding method in this paper. In particular, we design a secure weight modulation-based generator by introducing secure factors to hide secret messages in synthesised container images. In this manner, the synthesised results are modulated by secure factors and thus the secret messages are inaccessible when using fake factors, thus reducing the risk of message leakage. Furthermore, we design a difference predictor via the reconstruction of tampered container images together with an adversarial training strategy to iteratively update the estimation of hidden messages. This ensures robustness of recovering hidden messages, while degradation of synthesis fidelity is reduced since the generator is not included in the adversarial training. Extensive experimental results convincingly demonstrate that our proposed method is effective in avoiding message leakage and superior to other existing methods in terms of recovery robustness and synthesis fidelity.

PDF Details DOI

TIST Journal 2023 Journal Article

Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring

Wenyuan Yang
Shuo Shao
Yue Yang
Xiyao Liu
Ximeng Liu
Zhihua Xia
Gerald Schaefer
Hui Fang

Federated learning (FL) allows multiple participants to collaboratively build deep learning (DL) models without directly sharing data. Consequently, the issue of copyright protection in FL becomes important since unreliable participants may gain access to the jointly trained model. Application of homomorphic encryption (HE) in a secure FL framework prevents the central server from accessing plaintext models. Thus, it is no longer feasible to embed the watermark at the central server using existing watermarking schemes. In this article, we propose a novel client-side FL watermarking scheme to tackle the copyright protection issue in secure FL with HE. To the best of our knowledge, it is the first scheme to embed the watermark to models under a secure FL environment. We design a black-box watermarking scheme based on client-side backdooring to embed a pre-designed trigger set into an FL model by a gradient-enhanced embedding method. Additionally, we propose a trigger set construction mechanism to ensure that the watermark cannot be forged. Experimental results demonstrate that our proposed scheme delivers outstanding protection performance and robustness against various watermark removal attacks and ambiguity attack.

Details DOI

AAMAS Conference 2018 Conference Paper

Distributed Strategy Adaptation with a Prediction Function in Multi-Agent Task Allocation

Joanna Turner
Qinggang Meng
Gerald Schaefer
Andrea Soltoggio

Coordinating multiple agents to complete a set of tasks under time constraints is a complex problem. Distributed consensus-based task allocation algorithms address this problem without the need for human supervision. With such algorithms, agents add tasks to their own schedule according to specified allocation strategies. Various factors, such as the available resources and number of tasks, may affect the efficiency of a particular allocation strategy. The novel idea we suggest is that each individual agent can predict locally the best task inclusion strategy, based on the limited task assignment information communicated among networked agents. Using supervised classification learning, a function is trained to predict the most appropriate strategy between two well known insertion heuristics. Using the proposed method, agents are shown to correctly predict and select the optimal insertion heuristic to achieve the overall highest number of task allocations. The adaptive agents consistently match the performances of the best non-adaptive agents across a variety of scenarios. This study aims to demonstrate the possibility and potential performance benefits of giving agents greater decision making capabilities to independently adapt the task allocation process in line with the problem of interest.

PDF

AIIM Journal 2015 Journal Article

A hybrid cost-sensitive ensemble for imbalanced breast thermogram classification

Bartosz Krawczyk
Gerald Schaefer
Michał Woźniak

Objectives Early recognition of breast cancer, the most commonly diagnosed form of cancer in women, is of crucial importance, given that it leads to significantly improved chances of survival. Medical thermography, which uses an infrared camera for thermal imaging, has been demonstrated as a particularly useful technique for early diagnosis, because it detects smaller tumors than the standard modality of mammography. Methods and material In this paper, we analyse breast thermograms by extracting features describing bilateral symmetries between the two breast areas, and present a classification system for decision making. Clearly, the costs associated with missing a cancer case are much higher than those for mislabelling a benign case. At the same time, datasets contain significantly fewer malignant cases than benign ones. Standard classification approaches fail to consider either of these aspects. In this paper, we introduce a hybrid cost-sensitive classifier ensemble to address this challenging problem. Our approach entails a pool of cost-sensitive decision trees which assign a higher misclassification cost to the malignant class, thereby boosting its recognition rate. A genetic algorithm is employed for simultaneous feature selection and classifier fusion. As an optimisation criterion, we use a combination of misclassification cost and diversity to achieve both a high sensitivity and a heterogeneous ensemble. Furthermore, we prune our ensemble by discarding classifiers that contribute minimally to the decision making. Results For a challenging dataset of about 150 thermograms, our approach achieves an excellent sensitivity of 83. 10%, while maintaining a high specificity of 89. 44%. This not only signifies improved recognition of malignant cases, it also statistically outperforms other state-of-the-art algorithms designed for imbalanced classification, and hence provides an effective approach for analysing breast thermograms. Conclusions Our proposed hybrid cost-sensitive ensemble can facilitate a highly accurate early diagnostic of breast cancer based on thermogram features. It overcomes the difficulties posed by the imbalanced distribution of patients in the two analysed groups.

Details DOI

ICRA Conference 2015 Conference Paper

Increasing allocated tasks with a time minimization algorithm for a search and rescue scenario

Joanna Turner
Qinggang Meng
Gerald Schaefer

Rescue missions require both speed to meet strict time constraints and maximum use of resources. This study presents a Task Swap Allocation (TSA) algorithm that increases vehicle allocation with respect to the state-of-the-art consensus-based bundle algorithm and one of its extensions, while meeting time constraints. The novel idea is to enable an online reconfiguration of task allocation among distributed and networked vehicles. The proposed strategy reallocates tasks among vehicles to create feasible spaces for unallocated tasks, thereby optimizing the total number of allocated tasks. The algorithm is shown to be efficient with respect to previous methods because changes are made to a task list only once a suitable space in a schedule has been identified. Furthermore, the proposed TSA can be employed as an extension for other distributed task allocation algorithms with similar constraints to improve performance by escaping local optima and by reacting to dynamic environments.

Details

AIIM Journal 2014 Journal Article

Vicinal support vector classifier using supervised kernel-based clustering

Xulei Yang
Aize Cao
Qing Song
Gerald Schaefer
Yi Su

Objective Support vector machines (SVMs) have drawn considerable attention due to their high generalisation ability and superior classification performance compared to other pattern recognition algorithms. However, the assumption that the learning data is identically generated from unknown probability distributions may limit the application of SVMs for real problems. In this paper, we propose a vicinal support vector classifier (VSVC) which is shown to be able to effectively handle practical applications where the learning data may originate from different probability distributions. Methods The proposed VSVC method utilises a set of new vicinal kernel functions which are constructed based on supervised clustering in the kernel-induced feature space. Our proposed approach comprises two steps. In the clustering step, a supervised kernel-based deterministic annealing (SKDA) clustering algorithm is employed to partition the training data into different soft vicinal areas of the feature space in order to construct the vicinal kernel functions. In the training step, the SVM technique is used to minimise the vicinal risk function under the constraints of the vicinal areas defined in the SKDA clustering step. Results Experimental results on both artificial and real medical datasets show our proposed VSVC achieves better classification accuracy and lower computational time compared to a standard SVM. For an artificial dataset constructed from non-separated data, the classification accuracy of VSVC is between 95. 5% and 96. 25% (using different cluster numbers) which compares favourably to the 94. 5% achieved by SVM. The VSVC training time is between 8. 75s and 17. 83s (for 2–8 clusters), considerable less than the 65. 0s required by SVM. On a real mammography dataset, the best classification accuracy of VSVC is 85. 7% and thus clearly outperforms a standard SVM which obtains an accuracy of only 82. 1%. A similar performance improvement is confirmed on two further real datasets, a breast cancer dataset (74. 01% vs. 72. 52%) and a heart dataset (84. 77% vs. 83. 81%), coupled with a reduction in terms of learning time (32. 07s vs. 92. 08s and 25. 00s vs. 53. 31s, respectively). Furthermore, the VSVC results in the number of support vectors being equal to the specified cluster number, and hence in a much sparser solution compared to a standard SVM. Conclusion Incorporating a supervised clustering algorithm into the SVM technique leads to a sparse but effective solution, while making the proposed VSVC adaptive to different probability distributions of the training data.

Details DOI