Toby P. Breckon

Zhengdi Yu, Shaoli Huang, Chen Fang et al.

Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to impaired interaction, such as truncated hands, separate hands, or external occlusion. This paper presents ACR (Attention Collaboration-based Regressor), which makes the first attempt to reconstruct hands in arbitrary scenarios. To achieve this, ACR explicitly mitigates interdependencies between hands and between parts by leveraging center and part-based attention for feature extraction. However, reducing interdependence helps release the input constraint while weakening the mutual reasoning about reconstructing the interacting hands. Thus, based on center attention, ACR also learns cross-hand prior that handle the interacting hands better. We evaluate our method on various types of hand reconstruction datasets. Our method significantly outperforms the best interacting-hand approaches on the InterHand2.6M dataset while yielding comparable performance with the state-of-the-art single-hand methods on the FreiHand dataset. More qualitative results on in-the-wild and hand-object interaction datasets and web images/videos further demonstrate the effectiveness of our approach for arbitrary hand reconstruction. Our code is available at https://github.com/ZhengdiYu/Arbitrary-Hands-3D-Reconstruction.

Brian K. S. Isaac-Medina, Yona Falinie A. Gaus, Neelanjan Bhowmik et al.

Object detection is a pivotal task in computer vision that has received significant attention in previous years. Nonetheless, the capability of a detector to localise objects out of the training distribution remains unexplored. Whilst recent approaches in object-level out-of-distribution (OoD) detection heavily rely on class labels, such approaches contradict truly open-world scenarios where the class distribution is often unknown. In this context, anomaly detection focuses on detecting unseen instances rather than classifying detections as OoD. This work aims to bridge this gap by leveraging an open-world object detector and an OoD detector via virtual outlier synthesis. This is achieved by using the detector backbone features to first learn object pseudo-classes via self-supervision. These pseudo-classes serve as the basis for class-conditional virtual outlier sampling of anomalous features that are classified by an OoD head. Our approach empowers our overall object detector architecture to learn anomaly-aware feature representations without relying on class labels, hence enabling truly open-world object anomaly detection. Empirical validation of our approach demonstrates its effectiveness across diverse datasets encompassing various imaging modalities (visible, infrared, and X-ray). Moreover, our method establishes state-of-the-art performance on object-level anomaly detection, achieving an average recall score improvement of over 5.4% for natural images and 23.5% for a security X-ray dataset compared to the current approaches. In addition, our method detects anomalies in datasets where current approaches fail. Code available at https://github.com/KostadinovShalon/oln-ssos.

Benjamin Kiefer, Matej Kristan, Janez Perš et al.

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.

Li Li, Hubert P. H. Shum, Toby P. Breckon

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving. Existing work very often employs relatively large segmentation backbone networks to improve segmentation accuracy, at the expense of computational costs. In addition, many use uniform sampling to reduce ground truth data requirements for learning needed, often resulting in sub-optimal performance. To address these issues, we propose a new pipeline that employs a smaller architecture, requiring fewer ground-truth annotations to achieve superior segmentation accuracy compared to contemporary approaches. This is facilitated via a novel Sparse Depthwise Separable Convolution module that significantly reduces the network parameter count while retaining overall task performance. To effectively sub-sample our training data, we propose a new Spatio-Temporal Redundant Frame Downsampling (ST-RFD) method that leverages knowledge of sensor motion within the environment to extract a more diverse subset of training data frame samples. To leverage the use of limited annotated data samples, we further propose a soft pseudo-label method informed by LiDAR reflectivity. Our method outperforms contemporary semi-supervised work in terms of mIoU, using less labeled data, on the SemanticKITTI (59.5@5%) and ScribbleKITTI (58.1@5%) benchmark datasets, based on a 2.3x reduction in model parameters and 641x fewer multiply-add operations whilst also demonstrating significant performance improvement on limited training data (i.e., Less is More).

Neelanjan Bhowmik, Jack W. Barker, Yona Falinie A. Gaus et al.

Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression can cause severe decline in performance of deep Convolution Neural Network (CNN) architectures even when mild compression is applied and the resulting compressed imagery is visually identical. In this work, we apply the lossy JPEG compression method with six discrete levels of increasing compression {95, 75, 50, 15, 10, 5} to infrared band (thermal) imagery. Our study quantitatively evaluates the affect that increasing levels of lossy compression has upon the performance of characteristically diverse object detection architectures (Cascade-RCNN, FSAF and Deformable DETR) with respect to varying sizes of objects present in the dataset. When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0.823 with Cascade R-CNN across the FLIR dataset, outperforming prior work. The impact of the lossy compression is more extreme at higher compression levels (15, 10, 5) across all three CNN architectures. However, re-training models on lossy compressed imagery notably ameliorated performances for all three CNN models with an average increment of ~76% (at higher compression level 5). Additionally, we demonstrate the relative sensitivity of differing object areas {tiny, small, medium, large} with respect to the compression level. We show that tiny and small objects are more sensitive to compression than medium and large objects. Overall, Cascade R-CNN attains the maximal mAP across most of the object area categories.

Brian K. S. Isaac-Medina, Chris G. Willcocks, Toby P. Breckon

Neural Radiance Fields (NeRF) have attracted significant attention due to their ability to synthesize novel scene views with great accuracy. However, inherent to their underlying formulation, the sampling of points along a ray with zero width may result in ambiguous representations that lead to further rendering artifacts such as aliasing in the final scene. To address this issue, the recent variant mip-NeRF proposes an Integrated Positional Encoding (IPE) based on a conical view frustum. Although this is expressed with an integral formulation, mip-NeRF instead approximates this integral as the expected value of a multivariate Gaussian distribution. This approximation is reliable for short frustums but degrades with highly elongated regions, which arises when dealing with distant scene objects under a larger depth of field. In this paper, we explore the use of an exact approach for calculating the IPE by using a pyramid-based integral formulation instead of an approximated conical-based one. We denote this formulation as Exact-NeRF and contribute the first approach to offer a precise analytical solution to the IPE within the NeRF domain. Our exploratory work illustrates that such an exact formulation Exact-NeRF matches the accuracy of mip-NeRF and furthermore provides a natural extension to more challenging scenarios without further modification, such as in the case of unbounded scenes. Our contribution aims to both address the hitherto unexplored issues of frustum approximation in earlier NeRF work and additionally provide insight into the potential future consideration of analytical solutions in future NeRF extensions.

Li Li, Hubert P. H. Shum, Toby P. Breckon

3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and two effective RAPiD-Seg variants, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets.

Jiaxu Liu, Zhengdi Yu, Toby P. Breckon et al.

Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is still a lack of investigation into fully unsupervised scene segmentation for point clouds, especially for holistic 3D scenes. This paper presents U3DS$^3$, as a step towards completely unsupervised point cloud segmentation for any holistic 3D scenes. To achieve this, U3DS$^3$ leverages a generalized unsupervised segmentation method for both object and background across both indoor and outdoor static 3D point clouds with no requirement for model pre-training, by leveraging only the inherent information of the point cloud to achieve full 3D scene segmentation. The initial step of our proposed approach involves generating superpoints based on the geometric characteristics of each scene. Subsequently, it undergoes a learning process through a spatial clustering-based methodology, followed by iterative training using pseudo-labels generated in accordance with the cluster centroids. Moreover, by leveraging the invariance and equivariance of the volumetric representations, we apply the geometric transformation on voxelized features to provide two sets of descriptors for robust representation learning. Finally, our evaluation provides state-of-the-art results on the ScanNet and SemanticKITTI, and competitive results on the S3DIS, benchmark datasets.

Mehdi Rafiei, Toby P. Breckon, Alexandros Iosifidis

Anomaly detection methods have demonstrated remarkable success across various applications. However, assessing their performance, particularly at the pixel-level, presents a complex challenge due to the severe imbalance that is most commonly present between normal and abnormal samples. Commonly adopted evaluation metrics designed for pixel-level detection may not effectively capture the nuanced performance variations arising from this class imbalance. In this paper, we dissect the intricacies of this challenge, underscored by visual evidence and statistical analysis, leading to delve into the need for evaluation metrics that account for the imbalance. We offer insights into more accurate metrics, using eleven leading contemporary anomaly detection methods on twenty-one anomaly detection problems. Overall, from this extensive experimental evaluation, we can conclude that Precision-Recall-based metrics can better capture relative method performance, making them more suitable for the task.

Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik et al.

Generating 3D images of complex objects conditionally from a few 2D views is a difficult synthesis problem, compounded by issues such as domain gap and geometric misalignment. For instance, a unified framework such as Generative Adversarial Networks cannot achieve this unless they explicitly define both a domain-invariant and geometric-invariant joint latent distribution, whereas Neural Radiance Fields are generally unable to handle both issues as they optimize at the pixel level. By contrast, we propose a simple and novel 2D to 3D synthesis approach based on conditional diffusion with vector-quantized codes. Operating in an information-rich code space enables high-resolution 3D synthesis via full-coverage attention across the views. Specifically, we generate the 3D codes (e.g. for CT images) conditional on previously generated 3D codes and the entire codebook of two 2D views (e.g. 2D X-rays). Qualitative and quantitative results demonstrate state-of-the-art performance over specialized methods across varied evaluation criteria, including fidelity metrics such as density, coverage, and distortion metrics for two complex volumetric imagery datasets from in real-world scenarios.

Seyma Yucer, Matt Poyser, Noura Al Moubayed et al.

Yes - This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject. We adopt a recently proposed racial phenotype-based bias analysis methodology to measure the effect of varying levels of lossy compression across racial phenotype categories. Additionally, we determine the relationship between chroma-subsampling and race-related phenotypes for recognition performance. Prior work investigates the impact of lossy JPEG compression algorithm on contemporary face recognition performance. However, there is a gap in how this impact varies with different race-related inter-sectional groups and the cause of this impact. Via an extensive experimental setup, we demonstrate that common lossy image compression approaches have a more pronounced negative impact on facial recognition performance for specific racial phenotype categories such as darker skin tones (by up to 34.55\%). Furthermore, removing chroma-subsampling during compression improves the false matching rate (up to 15.95\%) across all phenotype categories affected by the compression, including darker skin tones, wide noses, big lips, and monolid eye categories. In addition, we outline the characteristics that may be attributable as the underlying cause of such phenomenon for lossy compression algorithms such as JPEG.

Neelanjan Bhowmik, Toby P. Breckon

X-ray baggage security screening is in widespread use and crucial to maintaining transport security for threat/anomaly detection tasks. The automatic detection of anomaly, which is concealed within cluttered and complex electronics/electrical items, using 2D X-ray imagery is of primary interest in recent years. We address this task by introducing joint object sub-component level segmentation and classification strategy using deep Convolution Neural Network architecture. The performance is evaluated over a dataset of cluttered X-ray baggage security imagery, consisting of consumer electrical and electronics items using variants of dual-energy X-ray imagery (pseudo-colour, high, low, and effective-Z). The proposed joint sub-component level segmentation and classification approach achieve ~99% true positive and ~5% false positive for anomaly detection task.

Qian Wang, Toby P. Breckon

Prior feature transformation based approaches to Unsupervised Domain Adaptation (UDA) employ the deep features extracted by pre-trained deep models without fine-tuning them on the specific source or target domain data for a particular domain adaptation task. In contrast, end-to-end learning based approaches optimise the pre-trained backbones and the customised adaptation modules simultaneously to learn domain-invariant features for UDA. In this work, we explore the potential of combining fine-tuned features and feature transformation based UDA methods for improved domain adaptation performance. Specifically, we integrate the prevalent progressive pseudo-labelling techniques into the fine-tuning framework to extract fine-tuned features which are subsequently used in a state-of-the-art feature transformation based domain adaptation method SPL (Selective Pseudo-Labeling). Thorough experiments with multiple deep models including ResNet-50/101 and DeiT-small/base are conducted to demonstrate the combination of fine-tuned features and SPL can achieve state-of-the-art performance on several benchmark datasets.

William Prew, Toby P. Breckon, Magnus Bordewich et al.

Generalising robotic grasping to previously unseen objects is a key task in general robotic manipulation. The current method for training many antipodal generative grasping models rely on a binary ground truth grasp map generated from the centre thirds of correctly labelled grasp rectangles. However, these binary maps do not accurately reflect the positions in which a robotic arm can correctly grasp a given object. We propose a continuous Gaussian representation of annotated grasps to generate ground truth training data which achieves a higher success rate on a simulated robotic grasping benchmark. Three modern generative grasping networks are trained with either binary or Gaussian grasp maps, along with recent advancements from the robotic grasping literature, such as discretisation of grasp angles into bins and an attentional loss function. Despite negligible difference according to the standard rectangle metric, Gaussian maps better reproduce the training data and therefore improve success rates when tested on the same simulated robot arm by avoiding collisions with the object: achieving 87.94\% accuracy. Furthermore, the best performing model is shown to operate with a high success rate when transferred to a real robotic arm, at high inference speeds, without the need for transfer learning. The system is then shown to be capable of performing grasps on an antagonistic physical object dataset benchmark.

Li Li, Tanqiu Qiao, Hubert P. H. Shum et al.

3D point clouds are essential for perceiving outdoor scenes, especially within the realm of autonomous driving. Recent advances in 3D LiDAR Object Detection focus primarily on the spatial positioning and distribution of points to ensure accurate detection. However, despite their robust performance in variable conditions, these methods are hindered by their sole reliance on coordinates and point intensity, resulting in inadequate isometric invariance and suboptimal detection outcomes. To tackle this challenge, our work introduces Transformation-Invariant Local (TraIL) features and the associated TraIL-Det architecture. Our TraIL features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize the inherent isotropic radiation of LiDAR to enhance local representation, improve computational efficiency, and boost detection performance. To effectively process the geometric relations among points within each proposal, we propose a Multi-head self-Attention Encoder (MAE) with asymmetric geometric features to encode high-dimensional TraIL features into manageable representations. Our method outperforms contemporary self-supervised 3D object detection approaches in terms of mAP on KITTI (67.8, 20% label, moderate) and Waymo (68.9, 20% label, moderate) datasets under various label ratios (20%, 50%, and 100%).

Ghadah Alosaimi, Maha Alsayyari, Yixin Sun et al.

Brain-computer interfaces (BCIs) provide a hands-free control modality for mobile robotics, yet decoding user intent during real-world navigation remains challenging. This work presents a brain-robot control framework for offline decoding of driving commands during robotic rover operation. A 4WD Rover Pro platform was remotely operated by 12 participants who navigated a predefined route using a joystick, executing the commands forward, reverse, left, right, and stop. Electroencephalogram (EEG) signals were recorded with a 16-channel OpenBCI cap and aligned with motor actions at Delta = 0 ms and future prediction horizons (Delta > 0 ms). After preprocessing, several deep learning models were benchmarked, including convolutional neural networks, recurrent neural networks, and Transformer architectures. ShallowConvNet achieved the highest performance for both action prediction and intent prediction. By combining real-world robotic control with multi-horizon EEG intention decoding, this study introduces a reproducible benchmark and reveals key design insights for predictive deep learning-based BCI systems.

Ghadah Alosaimi, Hanadi Alhamdan, Wenke E et al.

Predicting driver intention from neurophysiological signals offers a promising pathway for enhancing proactive safety in advanced driver assistance systems, yet remains challenging in real-world driving due to EEG signal non-stationarity and the complexity of cognitive-motor preparation. This study proposes and evaluates an EEG-based driver intention prediction framework using a synchronised multi-sensor platform integrated into a real electric vehicle. A real-world on-road dataset was collected across 32 driving sessions, and 12 deep learning architectures were evaluated under consistent experimental conditions. Among the evaluated architectures, TSCeption achieved the highest average accuracy (0.907) and Macro-F1 score (0.901). The proposed framework demonstrates strong temporal stability, maintaining robust decoding performance up to 1000 ms before manoeuvre execution with minimal degradation. Furthermore, additional analyses reveal that minimal EEG preprocessing outperforms artefact-handling pipelines, and prediction performance peaks within a 400-600 ms interval, corresponding to a critical neural preparatory phase preceding driving manoeuvres. Overall, these findings support the feasibility of early and stable EEG-based driver intention decoding under real-world on-road conditions. Code: https://github.com/galosaimi/Mind2Drive.

Wenke E, Yixin Sun, Jiaxu Liu et al.

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.

Yixin Sun, Li Li, Wenke E et al.

Detecting traversable pathways in unstructured outdoor environments remains a significant challenge for autonomous robots, especially in critical applications such as wide-area search and rescue, as well as incident management scenarios like forest fires. Existing datasets and models primarily target urban settings or wide, vehicle-traversable off-road tracks, leaving a substantial gap in addressing the complexity of narrow, trail-like off-road scenarios. To address this, we introduce the Trail-based Off-road Multimodal Dataset (TOMD), a comprehensive dataset specifically designed for such environments. TOMD features high-fidelity multimodal sensor data -- including 128-channel LiDAR, stereo imagery, GNSS, IMU, and illumination measurements -- collected through repeated traversals under diverse conditions. We also propose a dynamic multiscale data fusion model for accurate traversable pathway prediction. The study analyzes the performance of early, cross, and mixed fusion strategies under varying illumination levels. Results demonstrate the effectiveness of our approach and the relevance of illumination in segmentation performance. We publicly release TOMD at https://github.com/yyyxs1125/TMOD to support future research in trail-based off-road navigation.

Jiaxu Liu, Li Li, Hubert P. H. Shum et al.

Diffusion models currently demonstrate impressive performance over various generative tasks. Recent work on image diffusion highlights the strong capabilities of Mamba (state space models) due to its efficient handling of long-range dependencies and sequential data modeling. Unfortunately, joint consideration of state space models with 3D point cloud generation remains limited. To harness the powerful capabilities of the Mamba model for 3D point cloud generation, we propose a novel diffusion framework containing dual latent Mamba block (DM-Block) and a time-variant frequency encoder (TF-Encoder). The DM-Block apply a space-filling curve to reorder points into sequences suitable for Mamba state-space modeling, while operating in a latent space to mitigate the computational overhead that arises from direct 3D data processing. Meanwhile, the TF-Encoder takes advantage of the ability of the diffusion model to refine fine details in later recovery stages by prioritizing key points within the U-Net architecture. This frequency-based mechanism ensures enhanced detail quality in the final stages of generation. Experimental results on the ShapeNet-v2 dataset demonstrate that our method achieves state-of-the-art performance (ShapeNet-v2: 0.14\% on 1-NNA-Abs50 EMD and 57.90\% on COV EMD) on certain metrics for specific categories while reducing computational parameters and inference time by up to 10$\times$ and 9$\times$, respectively. Source code is available in Supplementary Materials and will be released upon accpetance.

Fady Medhat, Mahnaz Mohammadi, Sardar Jaf et al.

Handling large corpuses of documents is of significant importance in many fields, no more so than in the areas of crime investigation and defence, where an organisation may be presented with a large volume of scanned documents which need to be processed in a finite time. However, this problem is exacerbated both by the volume, in terms of scanned documents and the complexity of the pages, which need to be processed. Often containing many different elements, which each need to be processed and understood. Text recognition, which is a primary task of this process, is usually dependent upon the type of text, being either handwritten or machine-printed. Accordingly, the recognition involves prior classification of the text category, before deciding on the recognition method to be applied. This poses a more challenging task if a document contains both handwritten and machine-printed text. In this work, we present a generic process flow for text recognition in scanned documents containing mixed handwritten and machine-printed text without the need to classify text in advance. We realize the proposed process flow using several open-source image processing and text recognition packages1. The evaluation is performed using a specially developed variant, presented in this work, of the IAM handwriting database, where we achieve an average transcription accuracy of nearly 80% for pages containing both printed and handwritten text.

Yona Falinie A. Gaus, Neelanjan Bhowmik, Brian K. S. Isaac-Medina et al.

The Segment Anything Model (SAM) is a deep neural network foundational model designed to perform instance segmentation which has gained significant popularity given its zero-shot segmentation ability. SAM operates by generating masks based on various input prompts such as text, bounding boxes, points, or masks, introducing a novel methodology to overcome the constraints posed by dataset-specific scarcity. While SAM is trained on an extensive dataset, comprising ~11M images, it mostly consists of natural photographic images with only very limited images from other modalities. Whilst the rapid progress in visual infrared surveillance and X-ray security screening imaging technologies, driven forward by advances in deep learning, has significantly enhanced the ability to detect, classify and segment objects with high accuracy, it is not evident if the SAM zero-shot capabilities can be transferred to such modalities. This work assesses SAM capabilities in segmenting objects of interest in the X-ray/infrared modalities. Our approach reuses the pre-trained SAM with three different prompts: bounding box, centroid and random points. We present quantitative/qualitative results to showcase the performance on selected datasets. Our results show that SAM can segment objects in the X-ray modality when given a box prompt, but its performance varies for point prompts. Specifically, SAM performs poorly in segmenting slender objects and organic materials, such as plastic bottles. We find that infrared objects are also challenging to segment with point prompts given the low-contrast nature of this modality. This study shows that while SAM demonstrates outstanding zero-shot capabilities with box prompts, its performance ranges from moderate to poor for point prompts, indicating that special consideration on the cross-modal generalisation of SAM is needed when considering use on X-ray/infrared imagery.

Seyma Yucer, Amir Atapour Abarghouei, Noura Al Moubayed et al.

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.

Matt Poyser, Toby P. Breckon

In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilizing an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image within the global dataset in logarithmic time. Via curriculum learning, we then dynamically re-formulate an unbiased subsample dataset for NAS optimisation, upon which the current NAS solution architecture performs poorly. We show that our DDS-NAS framework speeds up gradient-based NAS strategies by up to 27x without loss in performance. By maximising the contribution of each image sample during training, we reduce the duration of a NAS training cycle and the number of iterations required for convergence.

Brian K. S. Isaac-Medina, Toby P. Breckon

Deep neural networks have demonstrated great generalization capabilities for tasks whose training and test sets are drawn from the same distribution. Nevertheless, out-of-distribution (OOD) detection remains a challenging task that has received significant attention in recent years. Specifically, OOD detection refers to the detection of instances that do not belong to the training distribution, while still having good performance on the in-distribution task (e.g., classification or object detection). Recent work has focused on generating synthetic outliers and using them to train an outlier detector, generally achieving improved OOD detection than traditional OOD methods. In this regard, outliers can be generated either in feature or pixel space. Feature space driven methods have shown strong performance on both the classification and object detection tasks, at the expense that the visualization of training outliers remains unknown, making further analysis on OOD failure modes challenging. On the other hand, pixel space outlier generation techniques enabled by diffusion models have been used for image classification using, providing improved OOD detection performance and outlier visualization, although their adaption to the object detection task is as yet unexplored. We therefore introduce Dream-Box, a method that provides a link to object-wise outlier generation in the pixel space for OOD detection. Specifically, we use diffusion models to generate object-wise outliers that are used to train an object detector for an in-distribution task and OOD detection. Our method achieves comparable performance to previous traditional methods while being the first technique to provide concrete visualization of generated OOD objects.

Wenke E, Chao Yuan, Li Li et al.

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.

Brian K. S. Isaac-Medina, Mauricio Che, Yona F. A. Gaus et al.

Modern machine learning models, that excel on computer vision tasks such as classification and object detection, are often overconfident in their predictions for Out-of-Distribution (OOD) examples, resulting in unpredictable behaviour for open-set environments. Recent works have demonstrated that the free energy score is an effective measure of uncertainty for OOD detection given its close relationship to the data distribution. However, despite free energy-based methods representing a significant empirical advance in OOD detection, our theoretical analysis reveals previously unexplored and inherent vulnerabilities within the free energy score formulation such that in-distribution and OOD instances can have distinct feature representations yet identical free energy scores. This phenomenon occurs when the vector direction representing the feature space difference between the in-distribution and OOD sample lies within the null space of the last layer of a neural-based classifier. To mitigate these issues, we explore lower-dimensional feature spaces to reduce the null space footprint and introduce novel regularisation to maximize the least singular value of the final linear layer, hence enhancing inter-sample free energy separation. We refer to these techniques as Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection (FEVER-OOD). Our experiments show that FEVER-OOD techniques achieve state of the art OOD detection in Imagenet-100, with average OOD false positive rate (at 95% true positive rate) of 35.83% when used with the baseline Dream-OOD model.

Li Li, Khalid N. Ismail, Hubert P. H. Shum et al.

We present DurLAR, a high-fidelity 128-channel 3D LiDAR dataset with panoramic ambient (near infrared) and reflectivity imagery, as well as a sample benchmark task using depth estimation for autonomous driving applications. Our driving platform is equipped with a high resolution 128 channel LiDAR, a 2MPix stereo camera, a lux meter and a GNSS/INS system. Ambient and reflectivity images are made available along with the LiDAR point clouds to facilitate multi-modal use of concurrent ambient and reflectivity scene information. Leveraging DurLAR, with a resolution exceeding that of prior benchmarks, we consider the task of monocular depth estimation and use this increased availability of higher resolution, yet sparse ground truth scene depth information to propose a novel joint supervised/self-supervised loss formulation. We compare performance over both our new DurLAR dataset, the established KITTI benchmark and the Cityscapes dataset. Our evaluation shows our joint use supervised and self-supervised loss terms, enabled via the superior ground truth resolution and availability within DurLAR improves the quantitative and qualitative performance of leading contemporary monocular depth estimation approaches (RMSE=3.639, Sq Rel=0.936).

Seyma Yucer, Furkan Tektas, Noura Al Moubayed et al.

Facial recognition is one of the most academically studied and industrially developed areas within computer vision where we readily find associated applications deployed globally. This widespread adoption has uncovered significant performance variation across subjects of different racial profiles leading to focused research attention on racial bias within face recognition spanning both current causation and future potential solutions. In support, this study provides an extensive taxonomic review of research on racial bias within face recognition exploring every aspect and stage of the face recognition processing pipeline. Firstly, we discuss the problem definition of racial bias, starting with race definition, grouping strategies, and the societal implications of using race or race-related groupings. Secondly, we divide the common face recognition processing pipeline into four stages: image acquisition, face localisation, face representation, face verification and identification, and review the relevant corresponding literature associated with each stage. The overall aim is to provide comprehensive coverage of the racial bias problem with respect to each and every stage of the face recognition processing pipeline whilst also highlighting the potential pitfalls and limitations of contemporary mitigation strategies that need to be considered within future research endeavours or commercial applications alike.

Sam Bond-Taylor, Peter Hessey, Hiroshi Sasaki et al.

Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high computational requirements. Recent Vector-Quantized image models have overcome this limitation of image resolution but are prohibitively slow and unidirectional as they generate tokens via element-wise autoregressive sampling from the prior. By contrast, in this paper we propose a novel discrete diffusion probabilistic model prior which enables parallel prediction of Vector-Quantized tokens by using an unconstrained Transformer architecture as the backbone. During training, tokens are randomly masked in an order-agnostic manner and the Transformer learns to predict the original tokens. This parallelism of Vector-Quantized token prediction in turn facilitates unconditional generation of globally consistent high-resolution and diverse imagery at a fraction of the computational expense. In this manner, we can generate image resolutions exceeding that of the original training set samples whilst additionally provisioning per-image likelihood estimates (in a departure from generative adversarial approaches). Our approach achieves state-of-the-art results in terms of Density (LSUN Bedroom: 1.51; LSUN Churches: 1.12; FFHQ: 1.20) and Coverage (LSUN Bedroom: 0.83; LSUN Churches: 0.73; FFHQ: 0.80), and performs competitively on FID (LSUN Bedroom: 3.64; LSUN Churches: 4.07; FFHQ: 6.11) whilst offering advantages in terms of both computation and reduced training set requirements.

Qian Wang, Fanlin Meng, Toby P. Breckon

Domain adaptation solves image classification problems in the target domain by taking advantage of the labelled source data and unlabelled target data. Usually, the source and target domains share the same set of classes. As a special case, Open-Set Domain Adaptation (OSDA) assumes there exist additional classes in the target domain but not present in the source domain. To solve such a domain adaptation problem, our proposed method learns discriminative common subspaces for the source and target domains using a novel Open-Set Locality Preserving Projection (OSLPP) algorithm. The source and target domain data are aligned in the learned common spaces class-wisely. To handle the open-set classification problem, our method progressively selects target samples to be pseudo-labelled as known classes and rejects the outliers if they are detected as from unknown classes. The common subspace learning algorithm OSLPP simultaneously aligns the labelled source data and pseudo-labelled target data from known classes and pushes the rejected target data away from the known classes. The common subspace learning and the pseudo-labelled sample selection/rejection facilitate each other in an iterative learning framework and achieves state-of-the-art performance on benchmark datasets Office-31 and Office-Home with the average HOS of 87.4% and 67.0% respectively.

Seyma Yucer, Furkan Tektas, Noura Al Moubayed et al.

Recent work reports disparate performance for intersectional racial groups across face recognition tasks: face verification and identification. However, the definition of those racial groups has a significant impact on the underlying findings of such racial bias analysis. Previous studies define these groups based on either demographic information (e.g. African, Asian etc.) or skin tone (e.g. lighter or darker skins). The use of such sensitive or broad group definitions has disadvantages for bias investigation and subsequent counter-bias solutions design. By contrast, this study introduces an alternative racial bias analysis methodology via facial phenotype attributes for face recognition. We use the set of observable characteristics of an individual face where a race-related facial phenotype is hence specific to the human face and correlated to the racial profile of the subject. We propose categorical test cases to investigate the individual influence of those attributes on bias within face recognition tasks. We compare our phenotype-based grouping methodology with previous grouping strategies and show that phenotype-based groupings uncover hidden bias without reliance upon any potentially protected attributes or ill-defined grouping strategies. Furthermore, we contribute corresponding phenotype attribute category labels for two face recognition tasks: RFW for face verification and VGGFace2 (test set) for face identification.

Thomas W. Webb, Neelanjan Bhowmik, Yona Falinie A. Gaus et al.

The recent advancement in deep Convolutional Neural Network (CNN) has brought insight into the automation of X-ray security screening for aviation security and beyond. Here, we explore the viability of two recent end-to-end object detection CNN architectures, Cascade R-CNN and FreeAnchor, for prohibited item detection by balancing processing time and the impact of image data compression from an operational viewpoint. Overall, we achieve maximal detection performance using a FreeAnchor architecture with a ResNet50 backbone, obtaining mean Average Precision (mAP) of 87.7 and 85.8 for using the OPIXray and SIXray benchmark datasets, showing superior performance over prior work on both. With fewer parameters and less training time, FreeAnchor achieves the highest detection inference speed of ~13 fps (3.9 ms per image). Furthermore, we evaluate the impact of lossy image compression upon detector performance. The CNN models display substantial resilience to the lossy compression, resulting in only a 1.1% decrease in mAP at the JPEG compression level of 50. Additionally, a thorough evaluation of data augmentation techniques is provided, including adaptions of MixUp and CutMix strategy as well as other standard transformations, further improving the detection accuracy.

Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon

Automatic detection of prohibited items within complex and cluttered X-ray security imagery is essential to maintaining transport security, where prior work on automatic prohibited item detection focus primarily on pseudo-colour (rgb}) X-ray imagery. In this work we study the impact of variant X-ray imagery, i.e., X-ray energy response (high, low}) and effective-z compared to rgb, via the use of deep Convolutional Neural Networks (CNN) for the joint object detection and segmentation task posed within X-ray baggage security screening. We evaluate state-of-the-art CNN architectures (Mask R-CNN, YOLACT, CARAFE and Cascade Mask R-CNN) to explore the transferability of models trained with such 'raw' variant imagery between the varying X-ray security scanners that exhibits differing imaging geometries, image resolutions and material colour profiles. Overall, we observe maximal detection performance using CARAFE, attributable to training using combination of rgb, high, low, and effective-z X-ray imagery, obtaining 0.7 mean Average Precision (mAP) for a six class object detection problem. Our results also exhibit a remarkable degree of generalisation capability in terms of cross-scanner transferability (AP: 0.835/0.611) for a one class object detection problem by combining rgb, high, low, and effective-z imagery.

Jack W. Barker, Toby P. Breckon

Semi-supervised methods of anomaly detection have seen substantial advancement in recent years. Of particular interest are applications of such methods to diverse, real-world anomaly detection problems where anomalous variations can vary from the visually obvious to the very subtle. In this work, we propose a novel fine-grained VAE-GAN architecture trained in a semi-supervised manner in order to detect both visually distinct and subtle anomalies. With the use of a residually connected dual-feature extractor, a fine-grained discriminator and a perceptual loss function, we are able to detect subtle, low inter-class (anomaly vs. normal) variant anomalies with greater detection capability and smaller margins of deviation in AUC value during inference compared to prior work whilst also remaining time-efficient during inference. We achieve state of-the-art anomaly detection results when compared extensively with prior semi-supervised approaches across a multitude of anomaly detection benchmark tasks including trivial leave-one out tasks (CIFAR-10 - AUPRCavg: 0.91; MNIST - AUPRCavg: 0.90) in addition to challenging real-world anomaly detection tasks (plant leaf disease - AUC: 0.776; threat item X-ray - AUC: 0.51), video frame-level anomaly detection (UCSDPed1 - AUC: 0.95) and high frequency texture with object anomalous defect detection (MVTEC - AUCavg: 0.83).

Daniel Organisciak, Matthew Poyser, Aishah Alsehaim et al.

As unmanned aerial vehicles (UAVs) become more accessible with a growing range of applications, the potential risk of UAV disruption increases. Recent development in deep learning allows vision-based counter-UAV systems to detect and track UAVs with a single camera. However, the coverage of a single camera is limited, necessitating the need for multicamera configurations to match UAVs across cameras - a problem known as re-identification (reID). While there has been extensive research on person and vehicle reID to match objects across time and viewpoints, to the best of our knowledge, there has been no research in UAV reID. UAVs are challenging to re-identify: they are much smaller than pedestrians and vehicles and they are often detected in the air so appear at a greater range of angles. Because no UAV data sets currently use multiple cameras, we propose the first new UAV re-identification data set, UAV-reID, that facilitates the development of machine learning solutions in this emerging area. UAV-reID has two settings: Temporally-Near to evaluate performance across views to assist tracking frameworks, and Big-to-Small to evaluate reID performance across scale and to allow early reID when UAVs are detected from a long distance. We conduct a benchmark study by extensively evaluating different reID backbones and loss functions. We demonstrate that with the right setup, deep networks are powerful enough to learn good representations for UAVs, achieving 81.9% mAP on the Temporally-Near setting and 46.5% on the challenging Big-to-Small setting. Furthermore, we find that vision transformers are the most robust to extreme variance of scale.

Hiroshi Sasaki, Chris G. Willcocks, Toby P. Breckon

We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain by minimising a denoising score matching objective conditioned on the other domain. In particular, we update both domain translation models simultaneously, and we generate target domain images by a denoising Markov Chain Monte Carlo approach that is conditioned on the input source domain images, based on Langevin dynamics. Our approach provides stable model training for image-to-image translation and generates high-quality image outputs. This enables state-of-the-art Fréchet Inception Distance (FID) performance on several public datasets, including both colour and multispectral imagery, significantly outperforming the contemporary adversarial image-to-image translation methods.

Brian K. S. Isaac-Medina, Matt Poyser, Daniel Organisciak et al.

Unmanned Aerial Vehicles (UAV) can pose a major risk for aviation safety, due to both negligent and malicious use. For this reason, the automated detection and tracking of UAV is a fundamental task in aerial security systems. Common technologies for UAV detection include visible-band and thermal infrared imaging, radio frequency and radar. Recent advances in deep neural networks (DNNs) for image-based object detection open the possibility to use visual information for this detection and tracking task. Furthermore, these detection architectures can be implemented as backbones for visual tracking systems, thereby enabling persistent tracking of UAV incursions. To date, no comprehensive performance benchmark exists that applies DNNs to visible-band imagery for UAV detection and tracking. To this end, three datasets with varied environmental conditions for UAV detection and tracking, comprising a total of 241 videos (331,486 images), are assessed using four detection architectures and three tracking frameworks. The best performing detector architecture obtains an mAP of 98.6% and the best performing tracking framework obtains a MOTA of 96.3%. Cross-modality evaluation is carried out between visible and infrared spectrums, achieving a maximal 82.8% mAP on visible images when training in the infrared modality. These results provide the first public multi-approach benchmark for state-of-the-art deep learning-based methods and give insight into which detection and tracking architectures are effective in the UAV domain.

Qian Wang, Toby P. Breckon

Automatic prohibited object detection within 2D/3D X-ray Computed Tomography (CT) has been studied in literature to enhance the aviation security screening at checkpoints. Deep Convolutional Neural Networks (CNN) have demonstrated superior performance in 2D X-ray imagery. However, there exists very limited proof of how deep neural networks perform in materials detection within volumetric 3D CT baggage screening imagery. We attempt to close this gap by applying Deep Neural Networks in 3D contraband substance detection based on their material signatures. Specifically, we formulate it as a 3D semantic segmentation problem to identify material types for all voxels based on which contraband materials can be detected. To this end, we firstly investigate 3D CNN based semantic segmentation algorithms such as 3D U-Net and its variants. In contrast to the original dense representation form of volumetric 3D CT data, we propose to convert the CT volumes into sparse point clouds which allows the use of point cloud processing approaches such as PointNet++ towards more efficient processing. Experimental results on a publicly available dataset (NEU ATR) demonstrate the effectiveness of both 3D U-Net and PointNet++ in materials detection in 3D CT imagery for baggage security screening.

Naif Alshammari, Samet Akcay, Toby P. Breckon

Robust semantic scene segmentation for automotive applications is a challenging problem in two key aspects: (1) labelling every individual scene pixel and (2) performing this task under unstable weather and illumination changes (e.g., foggy weather), which results in poor outdoor scene visibility. Such visibility limitations lead to non-optimal performance of generalised deep convolutional neural network-based semantic scene segmentation. In this paper, we propose an efficient end-to-end automotive semantic scene understanding approach that is robust to foggy weather conditions. As an end-to-end pipeline, our proposed approach provides: (1) the transformation of imagery from foggy to clear weather conditions using a domain transfer approach (correcting for poor visibility) and (2) semantically segmenting the scene using a competitive encoder-decoder architecture with low computational complexity (enabling real-time performance). Our approach incorporates RGB colour, depth and luminance images via distinct encoders with dense connectivity and features fusion to effectively exploit information from different inputs, which contributes to an optimal feature representation within the overall model. Using this architectural formulation with dense skip connections, our model achieves comparable performance to contemporary approaches at a fraction of the overall model complexity.

Naif Alshammari, Samet Akcay, Toby P. Breckon

Automotive scene understanding under adverse weather conditions raises a realistic and challenging problem attributable to poor outdoor scene visibility (e.g. foggy weather). However, because most contemporary scene understanding approaches are applied under ideal-weather conditions, such approaches may not provide genuinely optimal performance when compared to established a priori insights on extreme-weather understanding. In this paper, we propose a complex but competitive multi-task learning approach capable of performing in real-time semantic scene understanding and monocular depth estimation under foggy weather conditions by leveraging both recent advances in adversarial training and domain adaptation. As an end-to-end pipeline, our model provides a novel solution to surpass degraded visibility in foggy weather conditions by transferring scenes from foggy to normal using a GAN-based model. For optimal performance in semantic segmentation, our model generates depth to be used as complementary source information with RGB in the segmentation network. We provide a robust method for foggy scene understanding by training two models (normal and foggy) simultaneously with shared weights (each model is trained on each weather condition independently). Our model incorporates RGB colour, depth, and luminance images via distinct encoders with dense connectivity and features fusing, and leverages skip connections to produce consistent depth and segmentation predictions. Using this architectural formulation with light computational complexity at inference time, we are able to achieve comparable performance to contemporary approaches at a fraction of the overall model complexity.

Qian Wang, Fanlin Meng, Toby P. Breckon

We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a unified classifier for both domains within a high-dimensional homogeneous feature space without explicit domain adaptation. To this end, we employ the effective Selective Pseudo-Labelling (SPL) techniques to take advantage of the unlabelled samples in the target domain. Surprisingly, data distribution discrepancy across the source and target domains can be well handled by a computationally simple classifier (e.g., a shallow Multi-Layer Perceptron) trained in the original feature space. Besides, we propose a novel generative model norm-VAE to generate synthetic features for the target domain as a data augmentation strategy to enhance classifier training. Experimental results on several benchmark datasets demonstrate the pseudo-labelling strategy itself can lead to comparable performance to many state-of-the-art methods whilst the use of norm-VAE for feature augmentation can further improve the performance in most cases. As a result, our proposed methods (i.e. naive-SPL and norm-VAE-SPL) can achieve new state-of-the-art performance with the average accuracy of 93.4% and 90.4% on Office-Caltech and ImageCLEF-DA datasets, and comparable performance on Digits, Office31 and Office-Home datasets with the average accuracy of 97.2%, 87.6% and 67.9% respectively.

William Thomson, Neelanjan Bhowmik, Toby P. Breckon

Automatic visual fire detection is used to complement traditional fire detection sensor systems (smoke/heat). In this work, we investigate different Convolutional Neural Network (CNN) architectures and their variants for the non-temporal real-time bounds detection of fire pixel regions in video (or still) imagery. Two reduced complexity compact CNN architectures (NasNet-A-OnFire and ShuffleNetV2-OnFire) are proposed through experimental analysis to optimise the computational efficiency for this task. The results improve upon the current state-of-the-art solution for fire detection, achieving an accuracy of 95% for full-frame binary classification and 97% for superpixel localisation. We notably achieve a classification speed up by a factor of 2.3x for binary classification and 1.3x for superpixel localisation, with runtime of 40 fps and 18 fps respectively, outperforming prior work in the field presenting an efficient, robust and real-time solution for fire region detection. Subsequent implementation on low-powered devices (Nvidia Xavier-NX, achieving 49 fps for full-frame classification via ShuffleNetV2-OnFire) demonstrates our architectures are suitable for various real-world deployment applications.

Toby P. Breckon, Aishah Alsehaim

Video-based person re-identification has received increasing attention recently, as it plays an important role within surveillance video analysis. Video-based Re-ID is an expansion of earlier image-based re-identification methods by learning features from a video via multiple image frames for each person. Most contemporary video Re-ID methods utilise complex CNNbased network architectures using 3D convolution or multibranch networks to extract spatial-temporal video features. By contrast, in this paper, we illustrate superior performance from a simple single stream 2D convolution network leveraging the ResNet50-IBN architecture to extract frame-level features followed by temporal attention for clip level features. These clip level features can be generalised to extract video level features by averaging without any significant additional cost. Our approach uses best video Re-ID practice and transfer learning between datasets to outperform existing state-of-the-art approaches on the MARS, PRID2011 and iLIDS-VID datasets with 89:62%, 97:75%, 97:33% rank-1 accuracy respectively and with 84:61% mAP for MARS, without reliance on complex and memory intensive 3D convolutions or multi-stream networks architectures as found in other contemporary work. Conversely, our work shows that global features extracted by the 2D convolution network are a sufficient representation for robust state of the art video Re-ID.

Qian Wang, Neelanjan Bhowmik, Toby P. Breckon

Automatic detection of prohibited objects within passenger baggage is important for aviation security. X-ray Computed Tomography (CT) based 3D imaging is widely used in airports for aviation security screening whilst prior work on automatic prohibited item detection focus primarily on 2D X-ray imagery. These works have proven the possibility of extending deep convolutional neural networks (CNN) based automatic prohibited item detection from 2D X-ray imagery to volumetric 3D CT baggage security screening imagery. However, previous work on 3D object detection in baggage security screening imagery focused on the detection of one specific type of objects (e.g., either {\it bottles} or {\it handguns}). As a result, multiple models are needed if more than one type of prohibited item is required to be detected in practice. In this paper, we consider the detection of multiple object categories of interest using one unified framework. To this end, we formulate a more challenging multi-class 3D object detection problem within 3D CT imagery and propose a viable solution (3D RetinaNet) to tackle this problem. To enhance the performance of detection we investigate a variety of strategies including data augmentation and varying backbone networks. Experimentation carried out to provide both quantitative and qualitative evaluations of the proposed approach to multi-class 3D object detection within 3D CT baggage security screening imagery. Experimental results demonstrate the combination of the 3D RetinaNet and a series of favorable strategies can achieve a mean Average Precision (mAP) of 65.3\% over five object classes (i.e. {\it bottles, handguns, binoculars, glock frames, iPods}). The overall performance is affected by the poor performance on {\it glock frames} and {\it iPods} due to the lack of data and their resemblance with the baggage clutter.

Qian Wang, Toby P. Breckon

Domain adaptation approaches aim to exploit useful information from the source domain where supervised learning examples are easier to obtain to address a learning problem in the target domain where there is no or limited availability of such examples. In classification problems, domain adaptation has been studied under varying supervised, unsupervised and semi-supervised conditions. However, a common situation when the labelled samples are available for a subset of target domain classes has been overlooked. In this paper, we formulate this particular domain adaptation problem within a generalized zero-shot learning framework by treating the labelled source domain samples as semantic representations for zero-shot learning. For this particular problem, neither conventional domain adaptation approaches nor zero-shot learning algorithms directly apply. To address this generalized zero-shot domain adaptation problem, we present a novel Coupled Conditional Variational Autoencoder (CCVAE) which can generate synthetic target domain features for unseen classes from their source domain counterparts. Extensive experiments have been conducted on three domain adaptation datasets including a bespoke X-ray security checkpoint dataset to simulate a real-world application in aviation security. The results demonstrate the effectiveness of our proposed approach both against established benchmarks and in terms of real-world applicability.

Matt Poyser, Amir Atapour-Abarghouei, Toby P. Breckon

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.

Hiroshi Sasaki, Chris G. Willcocks, Toby P. Breckon

Machine learning driven object detection and classification within non-visible imagery has an important role in many fields such as night vision, all-weather surveillance and aviation security. However, such applications often suffer due to the limited quantity and variety of non-visible spectral domain imagery, in contrast to the high data availability of visible-band imagery that readily enables contemporary deep learning driven detection and classification approaches. To address this problem, this paper proposes and evaluates a novel data augmentation approach that leverages the more readily available visible-band imagery via a generative domain transfer model. The model can synthesise large volumes of non-visible domain imagery by image-to-image (I2I) translation from the visible image domain. Furthermore, we show that the generation of interpolated mixed class (non-visible domain) image examples via our novel Conditional CycleGAN Mixup Augmentation (C2GMA) methodology can lead to a significant improvement in the quality of non-visible domain classification tasks that otherwise suffer due to limited data availability. Focusing on classification within the Synthetic Aperture Radar (SAR) domain, our approach is evaluated on a variation of the Statoil/C-CORE Iceberg Classifier Challenge dataset and achieves 75.4% accuracy, demonstrating a significant improvement when compared against traditional data augmentation strategies (Rotation, Mixup, and MixCycleGAN).

Qian Wang, Toby P. Breckon

Heterogeneous Domain Adaptation (HDA) addresses the transfer learning problems where data from the source and target domains are of different modalities (e.g., texts and images) or feature dimensions (e.g., features extracted with different methods). It is useful for multi-modal data analysis. Traditional domain adaptation algorithms assume that the representations of source and target samples reside in the same feature space, hence are likely to fail in solving the heterogeneous domain adaptation problem. Contemporary state-of-the-art HDA approaches are usually composed of complex optimization objectives for favourable performance and are therefore computationally expensive and less generalizable. To address these issues, we propose a novel Cross-Domain Structure Preserving Projection (CDSPP) algorithm for HDA. As an extension of the classic LPP to heterogeneous domains, CDSPP aims to learn domain-specific projections to map sample features from source and target domains into a common subspace such that the class consistency is preserved and data distributions are sufficiently aligned. CDSPP is simple and has deterministic solutions by solving a generalized eigenvalue problem. It is naturally suitable for supervised HDA but has also been extended for semi-supervised HDA where the unlabelled target domain samples are available. Extensive experiments have been conducted on commonly used benchmark datasets (i.e. Office-Caltech, Multilingual Reuters Collection, NUS-WIDE-ImageNet) for HDA as well as the Office-Home dataset firstly introduced for HDA by ourselves due to its significantly larger number of classes than the existing ones (65 vs 10, 6 and 8). The experimental results of both supervised and semi-supervised HDA demonstrate the superior performance of our proposed method against contemporary state-of-the-art methods.

Seyma Yucer, Samet Akçay, Noura Al-Moubayed et al.

Whilst face recognition applications are becoming increasingly prevalent within our daily lives, leading approaches in the field still suffer from performance bias to the detriment of some racial profiles within society. In this study, we propose a novel adversarial derived data augmentation methodology that aims to enable dataset balance at a per-subject level via the use of image-to-image transformation for the transfer of sensitive racial characteristic facial features. Our aim is to automatically construct a synthesised dataset by transforming facial images across varying racial domains, while still preserving identity-related features, such that racially dependant features subsequently become irrelevant within the determination of subject identity. We construct our experiments on three significant face recognition variants: Softmax, CosFace and ArcFace loss over a common convolutional neural network backbone. In a side-by-side comparison, we show the positive impact our proposed technique can have on the recognition performance for (racial) minority groups within an originally imbalanced training dataset by reducing the pre-race variance in performance.