Aug. 29, 2022, 1:14 a.m. | Maxim Bonnaerens, Matthias Freiberger, Marian Verhelst, Joni Dambre

cs.CV updates on arXiv.org arxiv.org

In this work we propose a methodology to accurately evaluate and compare the
performance of efficient neural network building blocks for computer vision in
a hardware-aware manner. Our comparison uses pareto fronts based on randomly
sampled networks from a design space to capture the underlying
accuracy/complexity trade-offs. We show that our approach allows to match the
information obtained by previous comparison paradigms, but provides more
insights in the relationship between hardware cost and accuracy. We use our
methodology to analyze …

arxiv building computer computer vision cv evaluation hardware mobile vision

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote