Nearest Neighbour Score Estimators for Diffusion Generative Models

no code implementations • 12 Feb 2024 • Matthew Niedoba, Dylan Green, Saeid Naderiparizi, Vasileios Lioutas, Jonathan Wilder Lavington, Xiaoxuan Liang, Yunpeng Liu, Ke Zhang, Setareh Dabiri, Adam Ścibior, Berend Zwartsenberg, Frank Wood

Score function estimation is the cornerstone of both training and sampling from diffusion generative models.

Algorithms for Non-Negative Matrix Factorization on Noisy Data With Negative Values

1 code implementation • 8 Nov 2023 • Dylan Green, Stephen Bailey

In this paper we present two algorithms, Shift-NMF and Nearly-NMF, that can handle both the noisiness of the input data and also any introduced negativity.

Dimensionality Reduction

Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models

1 code implementation • 24 May 2023 • Setareh Dabiri, Vasileios Lioutas, Berend Zwartsenberg, Yunpeng Liu, Matthew Niedoba, Xiaoxuan Liang, Dylan Green, Justice Sefas, Jonathan Wilder Lavington, Frank Wood, Adam Scibior

When training object detection models on synthetic data, it is important to make the distribution of synthetic data as close as possible to the distribution of real data.

Object object-detection +1

Video Killed the HD-Map: Predicting Multi-Agent Behavior Directly From Aerial Images

no code implementations • 19 May 2023 • Yunpeng Liu, Vasileios Lioutas, Jonathan Wilder Lavington, Matthew Niedoba, Justice Sefas, Setareh Dabiri, Dylan Green, Xiaoxuan Liang, Berend Zwartsenberg, Adam Ścibior, Frank Wood

The development of algorithms that learn multi-agent behavioral models using human demonstrations has led to increasingly realistic simulations in the field of autonomous driving.

Autonomous Driving Trajectory Prediction