Skip to main content

Research Repository

Advanced Search

All Outputs (32)

Self-Regulated Sample Diversity in Large Language Models (2024)
Presentation / Conference Contribution
Liu, M., Frawley, J., Wyer, S., Shum, H. P. H., Uckelman, S. L., Black, S., & Willcocks, C. G. (2024, June). Self-Regulated Sample Diversity in Large Language Models. Presented at NAACL 2024: 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Mexico City

∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified States (2024)
Presentation / Conference Contribution
Bond-Taylor, S., & Willcocks, C. G. (2024, May). ∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified States. Presented at The International Conference on Learning Representations (ICLR), Vienna Austria

This paper introduces ∞-Diff, a generative diffusion model defined in an infinite-dimensional Hilbert space, which can model infinite resolution data. By training on randomly sampled subsets of coordinates and denoising content only at those location... Read More about ∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified States.

Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers (2023)
Presentation / Conference Contribution
Corona-Figueroa, A., Bond-Taylor, S., Bhowmik, N., Gaus, Y. F. A., Breckon, T. P., Shum, H. P., & Willcocks, C. G. (2023, October). Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers. Presented at ICCV23: 2023 IEEE/CVF International Conference on Computer Vision, Paris, France

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... Read More about Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers.

Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields (2023)
Presentation / Conference Contribution
Isaac-Medina, B., Willcocks, C., & Breckon, T. (2023, June). Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields. Presented at IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, Vancouver, BC

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 res... Read More about Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields.

Dynamic Unary Convolution in Transformers (2023)
Journal Article
Duan, H., Long, Y., Wang, S., Zhang, H., Willcocks, C. G., & Shao, L. (2023). Dynamic Unary Convolution in Transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 12747 - 12759. https://doi.org/10.1109/tpami.2022.3233482

It is uncertain whether the power of transformer architectures can complement existing convolutional neural networks. A few recent attempts have combined convolution with transformer design through a range of structures in series, where the main cont... Read More about Dynamic Unary Convolution in Transformers.

Denoising Diffusion Probabilistic Models on SO(3) for Rotational Alignment (2022)
Presentation / Conference Contribution
Leach, A., Schmon, S. M., Degiacomi, M. T., & Willcocks, C. G. (2022, April). Denoising Diffusion Probabilistic Models on SO(3) for Rotational Alignment. Presented at ICLR 2022 Workshop on Geometrical and Topological Representation Learning

Probabilistic diffusion models are capable of modeling complex data distributions on high-dimensional Euclidean spaces for a range applications. However, many real world tasks involve more complex structures such as data distributions defined on mani... Read More about Denoising Diffusion Probabilistic Models on SO(3) for Rotational Alignment.

Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes (2022)
Presentation / Conference Contribution
Bond-Taylor, S., Hessey, P., Sasaki, H., Breckon, T., & Willcocks, C. (2022, October). Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes. Presented at ECCV 2022: European Conference on Computer Vision, Tel Aviv, Israel

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... Read More about Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes.

MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray (2022)
Presentation / Conference Contribution
Corona-Figueroa, A., Frawley, J., Bond-Taylor, S., Bethapudi, S., Shum, H. P., & Willcocks, C. G. (2022, July). MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray. Presented at 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, Scotland

Computed tomography (CT) is an effective med-ical imaging modality, widely used in the field of clinical medicine for the diagnosis of various pathologies. Advances in Multidetector CT imaging technology have enabled additional functionalities, inclu... Read More about MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray.

Multi-view Vision Transformers for Object Detection (2022)
Presentation / Conference Contribution
Isaac-Medina, B., Willcocks, C., & Breckon, T. (2022, August). Multi-view Vision Transformers for Object Detection. Presented at International Conference on Pattern Recognition, Montreal, Canada

Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery (2022)
Presentation / Conference Contribution
Isaac-Medina, B., Bhowmik, N., Willcocks, C., & Breckon, T. (2022, June). Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery. Presented at 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, Louisiana

Dual-energy X-ray scanners are used for aviation security screening given their capability to discriminate materials inside passenger baggage. To facilitate manual operator inspection, a pseudo-colouring is assigned to the effective composition of th... Read More about Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery.

AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise (2022)
Presentation / Conference Contribution
Wyatt, J., Leach, A., Schmon, S. M., & Willcocks, C. G. (2022, June). AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise. Presented at 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, New Orleans, LA

Generative models have been shown to provide a powerful mechanism for anomaly detection by learning to model healthy or normal reference data which can subsequently be used as a baseline for scoring anomalies. In this work we consider denoising diffu... Read More about AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise.

Gradient Origin Networks (2021)
Presentation / Conference Contribution
Bond-Taylor, S., & Willcocks, C. G. (2021, May). Gradient Origin Networks. Presented at International Conference on Learning Representations, Vienna / Virtual

This paper proposes a new type of generative model that is able to quickly learn a latent representation without an encoder. This is achieved using empirical Bayes to calculate the expectation of the posterior, which is implemented by initialising a... Read More about Gradient Origin Networks.

Robust 3D U-Net Segmentation of Macular Holes (2021)
Presentation / Conference Contribution
Frawley, J., Willcocks, C. G., Habib, M., Geenen, C., Steel, D. H., & Obara, B. (2021, December). Robust 3D U-Net Segmentation of Macular Holes. Presented at The 29th Irish Conference on Artificial Intelligence and Cognitive Science 2021, Dublin, Republic of Ireland, December 9-10, 2021, Dublin, Ireland

Macular holes are a common eye condition which result in visual impairment. We look at the application of deep convolutional neural networks to the problem of macular hole segmentation. We use the 3D U-Net architecture as a basis and experiment with... Read More about Robust 3D U-Net Segmentation of Macular Holes.

Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark (2021)
Presentation / Conference Contribution
Isaac-Medina, B. K., Poyser, M., Organisciak, D., Willcocks, C. G., Breckon, T. P., & Shum, H. P. (2021, October). Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark. Presented at 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, Canada

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... Read More about Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark.

Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models (2021)
Journal Article
Bond-Taylor, S., Leach, A., Long, Y., & Willcocks, C. G. (2021). Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 7327-7347. https://doi.org/10.1109/tpami.2021.3116668

Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of which make trade-offs including run-time, diversit... Read More about Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models.

Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting (2021)
Presentation / Conference Contribution
Nguyen, B., Feldman, A., Bethapudi, S., Jennings, A., & Willcocks, C. G. (2021, April). Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting. Presented at 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, France

Medical segmentation is performed to determine the bounds of regions of interest (ROI) prior to surgery. By allowing the study of growth, structure, and behaviour of the ROI in the planning phase, critical information can be obtained, increasing the... Read More about Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting.

Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery (2021)
Presentation / Conference Contribution
Sasaki, H., Willcocks, C., & Breckon, T. (2021, January). Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy

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 limit... Read More about Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery.

Real Time Fencing Move Classification and Detection at Touch Time during a Fencing Match (2021)
Presentation / Conference Contribution
Sunal, C. E., Willcocks, C. G., & Obara, B. (2021, January). Real Time Fencing Move Classification and Detection at Touch Time during a Fencing Match. Presented at International Conference on Pattern Recognition (ICPR), Milan

Fencingis a fast-paced sport played with swords which are Épée, Foil, and Sabre. However, such fast-pace can cause referees to make wrong decisions. Review of slow-motion camera footage in tournaments helps referees' decision-making, but it interrupt... Read More about Real Time Fencing Move Classification and Detection at Touch Time during a Fencing Match.

Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery (2021)
Presentation / Conference Contribution
Isaac-Medina, B., Willcocks, C., & Breckon, T. (2021, January). Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy

Automatic detection for threat object items is an increasing emerging area of future application in X-ray security imagery. Although modern X-ray security scanners can provide two or more views, the integration of such object detectors across the vie... Read More about Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery.