4 papers
Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis
Brian K. S. Isaac-Medina, Yona Falinie A. Gaus, Neelanjan Bhowmik +1
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 o…
Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery
Yona Falinie A. Gaus, Neelanjan Bhowmik, Brian K. S. Isaac-Medina +1
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 s…
Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik +4
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…
Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption
Jack W Barker, Neelanjan Bhowmik, Yona Falinie A Gaus +1
Anomaly detection is the task of recognising novel samples which deviate significantly from pre-establishednormality. Abnormal classes are not present during training meaning that…