Biologically plausible and energy-efficient frameworks such as Spiking Neural Networks (SNNs) have not been sufficiently explored in low-level vision tasks. Taking image deraining as an example, this study addresses the representation of the inherent high-pass characteristics of spiking neurons, specifically in image deraining and innovatively proposes the Visual LIF (VLIF) neuron, overcoming the obstacle of lacking spatial contextual understanding present in traditional spiking neurons. To tackle the limitation of frequency-domain saturation inherent in conventional spiking neurons, we leverage the proposed VLIF to introduce the Spiking Decomposition and Enhancement Module and the lightweight Spiking Multi-scale Unit for hierarchical multi-scale representation learning. Extensive experiments across five benchmark deraining datasets demonstrate that our approach significantly outperforms state-of-the-art SNN-based deraining methods, achieving this superior performance with only 13% of their energy consumption. These findings establish a solid foundation for deploying SNNs in high-performance, energy-efficient low-level vision tasks.

We present the first cross-modality distillation framework specifically tailored for single-panoramic-camera Bird’s-Eye-View (BEV) segmentation. Our approach leverages a novel LiDAR image representation fused from range, intensity and ambient channels, together with a voxel-aligned view transformer that preserves spatial fidelity while enabling efficient BEV processing. During training, a high-capacity LiDAR and camera fusion Teacher network extracts both rich spatial and semantic features for cross-modality knowledge distillation into a lightweight Student network that relies solely on a single 360-degree panoramic camera image. Extensive experiments on the Dur360BEV dataset demonstrate that our teacher model significantly outperforms existing camera-based BEV segmentation methods, achieving a 25.6% IoU improvement. Meanwhile, the distilled Student network attains competitive performance with an 8.5% IoU gain and state-of-the-art inference speed of 31.2 FPS. Moreover, evaluations on KITTI-360 (two fisheye cameras) confirm that our distillation framework generalises to diverse camera setups, underscoring its feasibility and robustness. This approach reduces sensor complexity and deployment costs while providing a practical solution for efficient, low-cost BEV segmentation in real-world autonomous driving. The code is available at: https://github.com/Tom-E-Durham/KD360-VoxelBEV.

Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially challenging since it requires modeling extended temporal dynamics while remaining robust to contextual confounders. Existing approaches either depend on costly annotations or rely on unidirectional temporal modeling, making them vulnerable to spurious correlations and unstable long-term representations. To this end, we propose CaFlow, a unified framework that integrates counter-factual de-confounding with bidirectional time-conditioned flow. The Causal Counterfactual Regularization (CCR) module disentangles causal and confounding features in a self-supervised manner and enforces causal robustness through counterfactual interventions, while the BiT-Flow module models forward and backward dynamics with a cycle-consistency constraint to produce smoother and more coherent representations. Extensive experiments on multiple long-term AQA benchmarks demonstrate that CaFlow achieves state-of-the-art performance. Code is available at https://github.com/Harrison21/CaFlow

Infrared-visible object detection aims to leverage the complementary information between infrared and visible modalities to improve detection performance in challenging environments. However, existing infrared-visible object detection methods face several limitations: (1) difficulty in effectively extracting and decomposing modality-common and modality-specific features; (2) interference from modality-irrelevant or redundant information; and (3) insufficient fusion of cross-modal complementary cues. To address these issues, we propose a novel Modality Decomposition and Compensation Fusion Network (MDCF-Net). Specifically, MDCF-Net first decomposes the common and unique features across different modalities. It then performs selective enhancement and interaction between these features via cross-modality compensation. Finally, a dynamic fusion strategy based on spatial and channel attention is applied to adaptively integrate the enhanced features. Extensive experiments on two public datasets, LLVIP and FLIR, demonstrate that our proposed method achieves superior detection performance and exhibits robust generalisation across various challenging conditions. The Code is available at https://github.com/fanjiangtao666/MDCF-Net/tree/main

Long-term monitoring and exploration of extreme environments, such as underwater storage facilities, is costly, labor-intensive, and hazardous. Automating this process with low-cost, collaborative robots can greatly improve efficiency. These robots capture images from different positions, which must be processed simultaneously to create a spatio-temporal model of the facility. In this paper, we propose a novel approach that integrates data simulation, a multi-modal deep learning network for coordinate prediction, and image reassembly to address the challenges posed by environmental disturbances causing drift and rotation in the robots' positions and orientations. Our approach enhances the precision of alignment in noisy environments by integrating visual information from snapshots, global positional context from masks, and noisy coordinates. We validate our method through extensive experiments using synthetic data that simulate real-world robotic operations in underwater settings. The results demonstrate very high coordinate prediction accuracy and plausible image assembly, indicating the real-world applicability of our approach. The assembled images provide clear and coherent views of the underwater environment for effective monitoring and inspection, showcasing the potential for broader use in extreme settings, further contributing to improved safety, efficiency, and cost reduction in hazardous field monitoring.

We present Dur360BEV, a novel spherical camera autonomous driving dataset equipped with a high-resolution 128-channel 3D LiDAR and a RTK-refined GNSS/INS system, along with a benchmark architecture designed to generate Bird-Eye-View (BEV) maps using only a single spherical camera. This dataset and benchmark address the challenges of BEV generation in autonomous driving, particularly by reducing hardware complexity through the use of a single 360-degree camera instead of multiple perspective cameras. Within our benchmark architecture, we propose a novel spherical-image-to-BEV module that leverages spherical imagery and a refined sampling strategy to project features from 2D to 3D. Our approach also includes an innovative application of focal loss, specifically adapted to address the extreme class imbalance often encountered in BEV segmentation tasks, that demonstrates improved segmentation performance on the Dur360BEV dataset. The results show that our benchmark not only simplifies the sensor setup but also achieves competitive performance. Code + Dataset: https://github.com/Tom-E-DurhamJDur360BEV

Detecting traversable pathways in unstructured out-door environments remains a significant challenge for autonomous robots, especially in critical applications such as wide-area search and rescue, as well as in incident management scenarios such as forest fires. Current datasets and models primarily focus on either urban environments or wide vehicle-traversable off-road tracks, leaving a substantial gap in tackling the complexities of trail-based off-road scenarios. To address this issue, we introduce the Trail-based Off-road Multimodal Dataset (TOMD), a comprehensive dataset explicitly designed for narrow and unstructured trail-like environments. Our dataset features high-fidelity multimodal sensor data — including 128-channel LiDAR, stereo imagery, GNSS, IMU, and illumination measurements — collected through repeated runs across di-verse environmental conditions. In addition, we propose a novel dynamic multiscale data fusion model for precise traversable pathway prediction in trail-like areas. The study investigates the impact of various fusion processes — early, cross, and mixed — on model performance under different illumination levels: low-light, normal ambient lighting, and bright conditions. The results highlight the effectiveness of our approach, variation in performance across illumination levels, and the potential applicability of the dataset in diverse environmental conditions.Our work provides a valuable resource for advancing trail-based off-road navigation, and we openly publish our TOMD at https://github.com/yyyxs1125/TMOD to establish a future bench-mark in this research domain.

Continuous and reliable underwater monitoring is essential for assessing marine biodiversity, detecting ecological changes and supporting autonomous exploration in aquatic environments. Underwater monitoring platforms rely on mainly visual data for marine biodiversity analysis, ecological assessment and autonomous exploration. However, underwater environments present significant challenges due to light scattering, absorption and turbidity, which degrade image clarity and distort colour information, which makes accurate observation difficult. To address these challenges, we propose DEEP-SEA, a novel deep learning-based underwater image restoration model to enhance both low- and high-frequency information while preserving spatial structures. The proposed Dual-Frequency Enhanced Self-Attention Spatial and Frequency Modulator aims to adaptively refine feature representations in frequency domains and simultaneously spatial information for better structural preservation. Our comprehensive experiments on EUVP and LSUI datasets demonstrate the superiority over the state of the art in restoring fine-grained image detail and structural consistency. By effectively mitigating underwater visual degradation, DEEP-SEA has the potential to improve the reliability of underwater monitoring platforms for more accurate ecological observation, species identification and autonomous navigation.

Image inpainting aims to repair a partially damaged image based on the information from known regions of the images. Achieving semantically plausible inpainting results is particularly challenging because it requires the reconstructed regions to exhibit similar patterns to the semanticly consistent regions. This requires a model with a strong capacity to capture long-range dependencies. Existing models struggle in this regard due to the slow growth of receptive field for Convolutional Neural Networks (CNNs) based methods and patch-level interactions in Transformer-based methods, which are ineffective for capturing long-range dependencies. Motivated by this, we propose SEM-Net, a novel visual State Space model (SSM) vision network, modelling corrupted images at the pixel level while capturing long-range dependencies (LRDs) in state space, achieving a linear computational complexity. To address the inherent lack of spatial awareness in SSM, we introduce the Snake Mamba Block (SMB) and Spatially-Enhanced Feed-forward Network. These innovations enable SEM-Net to outperform state-of-the-art inpainting methods on two distinct datasets, showing significant improvements in capturing LRDs and enhancement in spatial consistency. Additionally, SEM-Net achieves state-of-the-art performance on motion deblurring, demonstrating its generalizability. Our source code is available: https://github.com/ChrisChenl023/SEM-Net.

The boundless possibility of neural networks which can be used to solve a problem - each with different performance - leads to a situation where a Deep Learning expert is required to identify the best neural network. This goes against the hope of removing the need for experts. Neural Architecture Search (NAS) offers a solution to this by automatically identifying the best architecture. However, to date, NAS work has focused on a small set of datasets which we argue are not representative of real-world problems. We introduce eight new datasets created for a series of NAS Challenges: AddNIST, Language, MultNIST, CIFAR-Tile, Gutenberg, Isabella, GeoClassing, and Chesseract. These datasets and challenges are developed to direct attention to issues in NAS development and to encourage authors to consider how their models will perform on datasets unknown to them at development time. We present experimentation using standard Deep Learning methods as well as the best results from challenge participants.

Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces. Despite these challenges, such fine-grained control, by way of disentanglement is a crucial enabler for data-driven racial bias mitigation strategies across multiple automated facial analysis tasks, as it allows to analyse, characterise and synthesise human facial diversity. In this paper, we propose a novel GAN framework to enable fine-grained control over individual race-related phenotype attributes of the facial images. Our framework factors the latent (feature) space into elements that correspond to race-related facial phenotype representations, thereby separating phenotype aspects (e.g. skin, hair colour, nose, eye, mouth shapes), which are notoriously difficult to annotate robustly in real-world facial data. Concurrently, we also introduce a high quality augmented, diverse 2D face image dataset drawn from CelebA-HQ for GAN training. Unlike prior work, our framework only relies upon 2D imagery and related parameters to achieve state-of-the-art individual control over race-related phenotype attributes with improved photo-realistic output.

Large language models (LLMs) have recently seen huge growth in capability and usage. Within software engineering, LLMs are increasingly being used by developers to generate code. Code generated by an LLM can be seen essentially a continuous mapping from requirements to code. This represents a great opportunity within requirements engineering to use this mapping to provide traceability from requirements to LLM-generated code. The challenge is that the black-box nature of LLMs makes it difficult to trace requirements, while traditional approaches require extensive post-hoc testing or expert analysis. In this research preview, we explore the use of LLM explainability techniques to trace LLM-generated code back to requirements. By inspecting the gradients of LLM output, we develop a first attempt at tracing LLM inputs through to its generated code. We use this to estimate which low-level requirements have been met. Furthermore, through an automated iterative process, we re-query the LLM, instructing it to rewrite its code to meet the missing requirements. Our results suggest that the gradients of LLM outputs can be used to trace requirements through LLM code generation and that this traceability could potentially be used to improve generated code to better meet requirements. Future work is required to fully validate this result, but this represents a first step towards automatic traceability and verification of AI generated code.

Existing image inpainting methods leverage convolution-based downsampling approaches to reduce spatial dimensions. This may result in information loss from corrupted images where the available information is inherently sparse, especially for the scenario of large missing regions. Recent advances in self-attention mechanisms within transformers have led to significant improvements in many computer vision tasks including inpainting. However, limited by the computational costs, existing methods cannot fully exploit the efficacy of long-range modelling capabilities of such models. In this paper, we propose an end-to-end High-quality INpainting Transformer, abbreviated as HINT, which consists of a novel mask-aware pixel-shuffle downsampling module (MPD) to preserve the visible information extracted from the corrupted image while maintaining the integrity of the information available for highlevel inferences made within the model. Moreover, we propose a Spatially-activated Channel Attention Layer (SCAL), an efficient self-attention mechanism interpreting spatial awareness to model the corrupted image at multiple scales. To further enhance the effectiveness of SCAL, motivated by recent advanced in speech recognition, we introduce a sandwich structure that places feed-forward networks before and after the SCAL module. We demonstrate the superior performance of HINT compared to contemporary state-of-the-art models on four datasets, CelebA, CelebA-HQ, Places2, and Dunhuang.

Graph representation plays a key role in graph analytics to perform a variety of downstream machine-learning tasks. This paper presents a novel method for extracting expressive graph representation based on a combination of statistics captured from a graph and node properties. We use both local and global-level information along with the original node properties to extract a meaningful feature representation of the graph. This allows us to build expressive graph descriptors that can be run with limited training data and computational resources and achieve competitive results. We discuss the merits of the proposed approach in terms of sensitivity, running times, and stability. Our evaluation of various graph classification benchmark datasets shows that the proposed method either outperforms or provides similar results to state-of-the-art methods. We further outline the potential future directions in graph machine learning research.

Predicting the performance and energy consumption of computing hardware is critical for many modern applications. This will inform procurement decisions, deployment decisions, and autonomic scaling. Existing approaches to understanding the performance of hardware largely focus around benchmarking -- leveraging standardised workloads which seek to be representative of an end-user's needs. Two key challenges are present; benchmark workloads may not be representative of an end-user's workload, and benchmark scores are not easily obtained for all hardware. Within this paper, we demonstrate the potential to build Deep Learning models to predict benchmark scores for unseen hardware. We undertake our evaluation with the openly available SPEC 2017 benchmark results. We evaluate three different networks, one fully-connected network along with two Convolutional Neural Networks (one bespoke and one ResNet inspired) and demonstrate impressive R2 scores of 0.96, 0.98 and 0.94 respectively.

Skin cancer is the most common malignancy in the world. Automated skin cancer detection would significantly improve early detection rates and prevent deaths. To help with this aim, a number of datasets have been released which can be used to train Deep Learning systems – these have produced impressive results for classification. However, this only works for the classes they are trained on whilst they are incapable of identifying skin lesions from previously unseen classes, making them unconducive for clinical use. We could look to massively increase the datasets by including all possible skin lesions, though this would always leave out some classes. Instead, we evaluate Siamese Neural Networks (SNNs), which not only allows us to classify images of skin lesions, but also allow us to identify those images which are different from the trained classes – allowing us to determine that an image is not an example of our training classes. We evaluate SNNs on both dermoscopic and clinical images of skin lesions. We obtain top-1 classification accuracy levels of 74.33% and 85.61% on clinical and dermoscopic datasets, respectively. Although this is slightly lower than the state-of-the-art results, the SNN approach has the advantage that it can detect out-of-class examples. Our results highlight the potential of an SNN approach as well as pathways towards future clinical deployment.

Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible. In this work, we robustly remove bias and spurious variation from an automated melanoma classification pipeline using two leading bias unlearning techniques. We show that the biases introduced by surgical markings and rulers presented in previous studies can be reasonably mitigated using these bias removal methods. We also demonstrate the generalisation benefits of unlearning spurious variation relating to the imaging instrument used to capture lesion images. Our experimental results provide evidence that the effects of each of the aforementioned biases are notably reduced, with different debiasing techniques excelling at different tasks.

Text classification has long been a staple within Natural Language Processing (NLP) with applications spanning across diverse areas such as sentiment analysis, recommender systems and spam detection. With such a powerful solution, it is often tempting to use it as the go-to tool for all NLP problems since when you are holding a hammer, everything looks like a nail. However, we argue here that many tasks which are currently addressed using classification are in fact being shoehorned into a classification mould and that if we instead address them as a ranking problem, we not only improve the model, but we achieve better performance. We propose a novel end-to-end ranking approach consisting of a Transformer network responsible for producing representations for a pair of text sequences, which are in turn passed into a context aggregating network outputting ranking scores used to determine an ordering to the sequences based on some notion of relevance. We perform numerous experiments on publicly-available datasets and investigate the applications of ranking in problems often solved using classification. In an experiment on a heavily- skewed sentiment analysis dataset, converting ranking results to classification labels yields an approximately 22% improvement over state-of-the-art text classification, demonstrating the efficacy of text ranking over text classification in certain scenarios.

As online news has become increasingly popular and fake news increasingly prevalent, the ability to audit the veracity of online news content has become more important than ever. Such a task represents a binary classification challenge, for which transformers have achieved state-of-the-art results. Using the publicly available ISOT and Combined Corpus datasets, this study explores transformers’ abilities to identify fake news, with particular attention given to investigating generalisation to unseen datasets with varying styles, topics and class distributions. Moreover, we explore the idea that opinion-based news articles cannot be classified as real or fake due to their subjective nature and often sensationalised language, and propose a novel two-step classification pipeline to remove such articles from both model training and the final deployed inference system. Experiments over the ISOT and Combined Corpus datasets show that transformers achieve an increase in F1scores of up to 4.9% for out of distribution generalisation compared to baseline approaches, with a further increase of 10.1% following the implementation of our two-step classification pipeline. To the best of our knowledge, this study is the first to investigate generalisation of transformers in this context.

The use of mobiles phones when driving has been a major factor when it comes to road traffic i ncidents and the process of capturing such violations can be a laborious task. Advancements in both modern object detection frameworks and high-performance hardware has paved the way for a more automated approach when it comes to video surveillance. In this work, we propose a custom-trained state-of-the-art object detector to work with roadside cameras to capture driver phone usage without the need for human intervention. The proposed approach also addresses the issues caused by windscreen glare and introduces the steps required to remedy this. Twelve pre-trained models are fine-tuned w ith o ur c ustom d ataset using four popular object detection methods: YOLO, SSD, Faster R-CNN, and CenterNet. Out of all the object detectors tested, YOLO yields the highest accuracy levels of up to ∼96% (AP10) and frame rates of up to ∼30 FPS. DeepSORT object tracking algorithm is also integrated into the best-performing model in order to avoid logging duplicate violations.

Biases can filter into AI technology without our knowledge. Oftentimes, seminal deep learning networks champion increased accuracy above all else. In this paper, we attempt to alleviate biases encountered by semantic segmentation models in urban driving scenes, via an iteratively trained unlearning algorithm. Convolutional neural networks have been shown to rely on colour and texture rather than geometry. This raises issues when safety-critical applications, such as self-driving cars, encounter images with covariate shift at test time - induced by variations such as lighting changes or seasonality. Conceptual proof of bias unlearning has been shown on simple datasets such as MNIST. However, the strategy has never been applied to the safety-critical domain of pixel-wise semantic segmentation of highly variable training data - such as urban scenes. Trained models for both the baseline and bias unlearning scheme have been tested for performance on colour-manipulated validation sets showing a disparity of up to 85.50% in mIoU from the original RGB images - confirming segmentation networks strongly depend on the colour information in the training data to make their classification. The bias unlearning scheme shows improvements of handling this covariate shift of up to 61% in the best observed case - and performs consistently better at classifying the "human" and "vehicle" classes compared to the baseline model.

As cybercriminals scale up their operations to increase their profits or inflict greater harm, we argue that there is an equal need to respond to their threats by scaling up cyber-security. To achieve this goal, we have to develop a co-productive approach towards data collection and sharing by overcoming the cybersecurity data sharing paradox. This is where we all agree on the definition of the problem and end goal (improving cybersecurity and getting rid of cybercrime), but we disagree about how to achieve it and fail to work together efficiently. At the core of this paradox is the observation that public interests differ from private interests. As a result, industry and law enforcement take different approaches to the cybersecurity problem as they seek to resolve incidents in their own interests, which manifests in different data sharing practices between both and also other interested parties, such as cybersecurity researchers. The big question we ask is can these interests be reconciled to develop an interdisciplinary approach towards co-operation and sharing data. In essence, all three will have to co-own the problem in order to co-produce a solution. We argue that a few operational models with good practices exist that provide guides to a possible solution, especially multiple third-party ownership organisations which consolidate, anonymise and analyse data. To take this forward, we suggest the practical solution of organising co-productive data collection on a sectoral basis, but acknowledge that common standards for data collection will also have to be developed and agreed upon. We propose an initial set of best practices for building collaborations and sharing data and argue that these best practices need to be developed and standardised in order to mitigate the paradox.

With the growing significance of graphs as an effective representation of data in numerous applications, efficient graph analysis using modern machine learning is receiving a growing level of attention. Deep learning approaches often operate over the entire adjacency matrix - as the input and intermediate network layers are all designed in proportion to the size of the adjacency matrix - leading to intensive computation and large memory requirements as the graph size increases. It is therefore desirable to identify efficient measures to reduce both run-time and memory requirements allowing for the analysis of the largest graphs possible. The use of reduced precision operations within the forward and backward passes of a deep neural network along with novel specialised hardware in modern GPUs could offer promising avenues towards efficiency. In this paper, we provide an in-depth exploration of the use of reduced-precision operations, easily integrable into the highly popular PyTorch framework, and an analysis of the effects of Tensor Cores on graph convolutional neural networks. We perform an extensive experimental evaluation of three GPU architectures and two widely-used graph analysis tasks (vertex classification and link prediction) using well-known benchmark and synthetically generated datasets. Thus allowing us to make important observations on the effects of reduced-precision operations and Tensor Cores on computational and memory usage of graph convolutional neural networks - often neglected in the literature.

Recently, substantial progress has been made in the area of Brain-Computer Interface (BCI) using modern machine learning techniques to decode and interpret brain signals. While Electroencephalography (EEG) has provided a non-invasive method of interfacing with a human brain, the acquired data is often heavily subject and session dependent. This makes the seamless incorporation of such data into realworld applications intractable as the subject and session data variance can lead to long and tedious calibration requirements and cross-subject generalisation issues. Focusing on a Steady State Visual Evoked Potential (SSVEP) classification systems, we propose a novel means of generating highly-realistic synthetic EEG data invariant to any subject, session or other environmental conditions. Our approach, entitled the Subject Invariant SSVEP Generative Adversarial Network (SIS-GAN), produces synthetic EEG data from multiple SSVEP classes using a single network. Additionally, by taking advantage of a fixed-weight pre-trained subject classification network, we ensure that our generative model remains agnostic to subject-specific features and thus produces subject-invariant data that can be applied to new previously unseen subjects. Our extensive experimental evaluation demonstrates the efficacy of our synthetic data, leading to superior performance, with improvements of up to 16 percentage points in zero-calibration classification tasks when trained using our subject-invariant synthetic EEG signals.

Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks. Whilst the reported performance of these approaches is impressive, this study investigates the hitherto unapproached question of the impact of commonplace image and video compression techniques on the performance of such deep learning architectures. Focusing on the JPEG and H.264 (MPEG-4 AVC) as a representative proxy for contemporary lossy image/video compression techniques that are in common use within network-connected image/video devices and infrastructure, we examine the impact on performance across five discrete tasks: human pose estimation, semantic segmentation, object detection, action recognition, and monocular depth estimation. As such, within this study we include a variety of network architectures and domains spanning end-to-end convolution, encoder-decoder, region-based CNN (R-CNN), dual-stream, and generative adversarial networks (GAN). Our results show a non-linear and non-uniform relationship between network performance and the level of lossy compression applied. Notably, performance decreases significantly below a JPEG quality (quantization) level of 15% and a H.264 Constant Rate Factor (CRF) of 40. However, retraining said architectures on pre-compressed imagery conversely recovers network performance by up to 78.4% in some cases. Furthermore, there is a correlation between architectures employing an encoder-decoder pipeline and those that demonstrate resilience to lossy image compression. The characteristics of the relationship between input compression to output task performance can be used to inform design decisions within future image/video devices and infrastructure.

Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based model capable of performing two tasks:- sparse depth completion (i.e. generating complete dense scene depth given a sparse depth image as the input) and monocular depth estimation (i.e. predicting scene depth from a single RGB image) via two sub-networks jointly trained end to end using data randomly sampled from a publicly available corpus of synthetic and real-world images. The first sub-network generates a sparse depth image by learning lower level features from the scene and the second predicts a full dense depth image of the entire scene, leading to a better geometric and contextual understanding of the scene and, as a result, superior performance of the approach. The entire model can be used to infer complete scene depth from a single RGB image or the second network can be used alone to perform depth completion given a sparse depth input. Using adversarial training, a robust objective function, a deep architecture relying on skip connections and a blend of synthetic and real-world training data, our approach is capable of producing superior high quality scene depth. Extensive experimental evaluation demonstrates the efficacy of our approach compared to contemporary state-of-the-art techniques across both problem domains.

Newly emerging variants of ransomware pose an ever-growing threat to computer systems governing every aspect of modern life through the handling and analysis of big data. While various recent security-based approaches have focused on ransomware detection at the network or system level, easy-to-use post-infection ransomware classification for the lay user has not been attempted before. In this paper, we investigate the possibility of classifying the ransomware a system is infected with simply based on a screenshot of the splash screen or the ransom note captured using a consumer camera commonly found in any modern mobile device. To train and evaluate our system, we create a sample dataset of the splash screens of 50 well-known ransomware variants. In our dataset, only a single training image is available per ransomware. Instead of creating a large training dataset of ransomware screenshots, we simulate screenshot capture conditions via carefully-designed data augmentation techniques, enabling simple and efficient one-shot learning. Moreover, using model uncertainty obtained via Bayesian approximation, we ensure special input cases such as unrelated non-ransomware images and previously-unseen ransomware variants are correctly identified for special handling and not mis-classified. Extensive experimental evaluation demonstrates the efficacy of our work, with accuracy levels of up to 93.6% for ransomware classification.

With the recent growth in the number of malicious activities on the internet, cybersecurity research has seen a boost in the past few years. However, as certain variants of malware can provide highly lucrative opportunities for bad actors, significant resources are dedicated to innovations and improvements by vast criminal organisations. Among these forms of malware, ransomware has experienced a significant recent rise as it offers the perpetrators great financial incentive. Ransomware variants operate by removing system access from the user by either locking the system or encrypting some or all of the data, and subsequently demanding payment or ransom in exchange for returning system access or providing a decryption key to the victim. Due to the ubiquity of sensitive data in many aspects of modern life, many victims of such attacks, be they an individual home user or operators of a business, are forced to pay the ransom to regain access to their data, which in many cases does not happen as renormalisation of system operations is never guaranteed. As the problem of ransomware does not seem to be subsiding, it is very important to investigate the underlying forces driving and facilitating such attacks in order to create preventative measures. As such, in this paper, we discuss and provide further insight into variants of ransomware and their victims in order to understand how and why they have been targeted and what can be done to prevent or mitigate the effects of such attacks.

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently disregarded during the learning process, resulting in suboptimal performance on certain temporal inference tasks. To combat this, we introduce Temporal Neighbourhood Aggregation (TNA), a novel vertex representation model architecture designed to capture both topological and temporal information to directly predict future graph states. Our model exploits hierarchical recurrence at different depths within the graph to enable exploration of changes in temporal neighbourhoods, whilst requiring no additional features or labels to be present. The final vertex representations are created using variational sampling and are optimised to directly predict the next graph in the sequence. Our claims are supported by experimental evaluation on both real and synthetic benchmark datasets, where our approach demonstrates superior performance compared to competing methods, outperforming them at predicting new temporal edges by as much as 23% on real-world datasets, whilst also requiring fewer overall model parameters.

Robust geometric and semantic scene understanding is ever more important in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based approach capable of jointly performing geometric and semantic scene understanding, namely depth prediction (monocular depth estimation and depth completion) and semantic scene segmentation. Within a single temporally constrained recurrent network, our approach uniquely takes advantage of a complex series of skip connections, adversarial training and the temporal constraint of sequential frame recurrence to produce consistent depth and semantic class labels simultaneously. Extensive experimental evaluation demonstrates the efficacy of our approach compared to other contemporary state-of-the-art techniques.

Monocular depth estimation using novel learning-based approaches has recently emerged as a promising potential alternative to more conventional 3D scene capture technologies within real-world scenarios. Many such solutions often depend on large quantities of ground truth depth data, which is rare and often intractable to obtain. Others attempt to estimate disparity as an intermediary step using a secondary supervisory signal, leading to blurring and other undesirable artefacts. In this paper, we propose a monocular depth estimation approach, which employs a jointly-trained pixel-wise semantic understanding step to estimate depth for individually-selected groups of objects (segments) within the scene. The separate depth outputs are efficiently fused to generate the final result. This creates more simplistic learning objectives for the jointly-trained individual networks, leading to more accurate overall depth. Extensive experimentation demonstrates the efficacy of the proposed approach compared to contemporary state-of-the-art techniques within the literature.

Despite inherent ill-definition, anomaly detection is a research endeavour of great interest within machine learning and visual scene understanding alike. Most commonly, anomaly detection is considered as the detection of outliers within a given data distribution based on some measure of normality. The most significant challenge in real-world anomaly detection problems is that available data is highly imbalanced towards normality (i.e. non-anomalous) and contains at most a sub-set of all possible anomalous samples - hence limiting the use of well-established supervised learning methods. By contrast, we introduce an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain, and hence detect abnormality based on deviation from this model. Our proposed approach employs an encoder-decoder convolutional neural network with skip connections to thoroughly capture the multi-scale distribution of the normal data distribution in image space. Furthermore, utilizing an adversarial training scheme for this chosen architecture provides superior reconstruction both within image space and a lower-dimensional embedding vector space encoding. Minimizing the reconstruction error metric within both the image and hidden vector spaces during training aids the model to learn the distribution of normality as required. Higher reconstruction metrics during subsequent test and deployment are thus indicative of a deviation from this normal distribution, hence indicative of an anomaly. Experimentation over established anomaly detection benchmarks and challenging real-world datasets, within the context of X-ray security screening, shows the unique promise of such a proposed approach.

Despite significant recent progress in the area of Brain-Computer Interface (BCI), there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals in real-world environments. These include, but are not limited to, subject and session data variance, long and arduous calibration processes and predictive generalisation issues across different subjects or sessions. This implies that many downstream applications, including Steady State Visual Evoked Potential (SSVEP) based classification systems, can suffer from a shortage of reliable data. Generating meaningful and realistic synthetic data can therefore be of significant value in circumventing this problem. We explore the use of modern neural-based generative models trained on a limited quantity of EEG data collected from different subjects to generate supplementary synthetic EEG signal vectors, subsequently utilised to train an SSVEP classifier. Extensive experimental analysis demonstrates the efficacy of our generated data, leading to improvements across a variety of evaluations, with the crucial task of cross-subject generalisation improving by over 35% with the use of such synthetic data.

Monocular depth estimation using learning-based approaches has become promising in recent years. However, most monocular depth estimators either need to rely on large quantities of ground truth depth data, which is extremely expensive and difficult to obtain, or predict disparity as an intermediary step using a secondary supervisory signal leading to blurring and other artefacts. Training a depth estimation model using pixel-perfect synthetic data can resolve most of these issues but introduces the problem of domain bias. This is the inability to apply a model trained on synthetic data to real-world scenarios. With advances in image style transfer and its connections with domain adaptation (Maximum Mean Discrepancy), we take advantage of style transfer and adversarial training to predict pixel perfect depth from a single real-world color image based on training over a large corpus of synthetic environment data. Experimental results indicate the efficacy of our approach compared to contemporary state-of-the-art techniques.

We address the problem of hole filling in RGB-D (color and depth) images, obtained from either active or stereo based sensing, for the purposes of object removal and missing depth estimation. This is performed independently on the low frequency depth information (surface shape) and the high frequency depth detail (relief) by way of a Fourier space transform and classical Butterworth high/low pass filtering. The high frequency detail is then filled using a texture synthesis method, whilst the low frequency shape information is inpainted using structural inpainting. Here, a classical non-parametric sampling approach is extended, using the concept of query expansion, to perform high frequency depth synthesis with the final output then recombined in Fourier space. In order to improve the overall depth relief (D) and edge detail accuracy, color information (RGB) is also used to constrain the sampling process within high frequency component completion. Experimental results demonstrate the efficacy of the proposed method outperforming prior work for generalized depth filling in the presence of high frequency surface relief detail.