Reproduce “RedunCut: Measurement-Driven Sampling and Accuracy Performance Modeling for Low-Cost Live Video Analytics” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Gur-Eyal Sela, Kumar Krishna Agrawal, Bharathan Balaji, Joseph Gonzalez, Ion Stoica
RedunCut selects vision models for segments of live video, balancing inference compute against a target aggregate accuracy. It estimates whether sampling another model is worth its cost, then uses historical data and a lightweight k-nearest-neighbors predictor to estimate model accuracy without modifying the underlying models. On Waymo road-vehicle tracking, it reduces compute cost 19–62% versus Tiered-sampling at tested MOTA targets.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.