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 research trails →

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