Benjamin Biggs
YOU?
Author Swipe
View article: Diffusion Soup: Model Merging for Text-to-Image Diffusion Models
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models Open
We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our approach enables training-free continual learning and unlearn…
View article: ATHEENA: A Toolflow for Hardware Early-Exit Network Automation
ATHEENA: A Toolflow for Hardware Early-Exit Network Automation Open
The continued need for improvements in accuracy, throughput, and efficiency of Deep Neural Networks has resulted in a multitude of methods that make the most of custom architectures on FPGAs. These include the creation of hand-crafted netw…
View article: Shape of You: Precise 3D shape estimations for diverse body types
Shape of You: Precise 3D shape estimations for diverse body types Open
This paper presents Shape of You (SoY), an approach to improve the accuracy of 3D body shape estimation for vision-based clothing recommendation systems. While existing methods have successfully estimated 3D poses, there remains a lack of …
View article: Non-Submodular Maximization via the Greedy Algorithm and the Effects of Limited Information in Multi-Agent Execution
Non-Submodular Maximization via the Greedy Algorithm and the Effects of Limited Information in Multi-Agent Execution Open
We provide theoretical bounds on the worst case performance of the greedy algorithm in seeking to maximize a normalized, monotone, but not necessarily submodular objective function under a simple partition matroid constraint. We also provi…
View article: Experiments in Underwater Feature Tracking with Performance Guarantees Using a Small AUV
Experiments in Underwater Feature Tracking with Performance Guarantees Using a Small AUV Open
We present the results of experiments performed using a small autonomous underwater vehicle to determine the location of an isobath within a bounded area. The primary contribution of this work is to implement and integrate several recent d…
View article: High-level Synthesis using the Julia Language
High-level Synthesis using the Julia Language Open
The growing proliferation of FPGAs and High-level Synthesis (HLS) tools has led to a large interest in designing hardware accelerators for complex operations and algorithms. However, existing HLS toolflows typically require a significant a…
View article: 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data
3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data Open
We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views. In such cases, the visual evidence is usually insufficient to identify a 3D reconstruction uniquely, so we aim at recovering …
View article: Creatures great and SMAL: Recovering the shape and motion of animals\n from video
Creatures great and SMAL: Recovering the shape and motion of animals\n from video Open
We present a system to recover the 3D shape and motion of a wide variety of\nquadrupeds from video. The system comprises a machine learning front-end which\npredicts candidate 2D joint positions, a discrete optimization which finds\nkinema…
View article: The impact of unwashed aggregate on water quality emanating from permeable pavements
The impact of unwashed aggregate on water quality emanating from permeable pavements Open
Sustainable Drainage System (SuDS) technologies set out to mitigate the adverse effects of urban stormwater runoff, through a multi-objective approach. Permeable pavement systems (PPSs) are one of the most widely-adopted SuDS technologies …