NeurIPS 2023

Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception

Anurag Ghosh, Vaibhav Balloli, Akshay Nambi, Aditya Singh, Tanuja Ganu

Advances in Neural Information Processing Systems (NeurIPS)

Paper Code Project
Figure from “Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception”

Summary

A learned approximate-execution framework for streaming perception. Chanakya jointly considers scene content and system contention to pick run-time decisions (resolution, model, compute) that balance accuracy and latency, beating static and dynamic baselines on both server GPUs and edge devices.

How this fits together

See the full research lineage →

Topics

Cite this paper

@inproceedings{ghosh2023chanakya,
  title     = {Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception},
  author    = {Ghosh, Anurag and Balloli, Vaibhav and Nambi, Akshay and Singh, Aditya and Ganu, Tanuja},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2023}
}

← All publications