AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception

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

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learned Chanakya policy (R2) instead of best static policy Streamer s=600Faster R-CNN + Kalman Filter · Argoverse-HDsAP: 20.4 -> 21.3Improved
learned policy instead of AdaScale dynamic traditional policyStreamer + Kalman Filter · Argoverse-HDsAP: 13.8 -> 21.3Improved
add modified shrinking tail scheduler to Streamer + AdaScale (ablation)Streamer + AdaScale · Argoverse-HDsAP: 13.4 -> 13.8Improved
expert tuning of proposals (np=500) on Streamer s=600Streamer · Argoverse-HDsAP: 20.4 -> 20.9Improved
use R2 (advantage over fixed policy) instead of R1 reward (ablation)Chanakya · Argoverse-HDsAP: 21.0 -> 21.3Improved
use R2 instead of R1 reward (ablation)Chanakya · ImageNet-VIDsAP: 37.5 -> 37.2Hurt
use R2 instead of R1 reward on Xavier NX (ablation)Chanakya · ImageNet-VID Xavier NXsAP: 19.4 -> 22.4Improved
learned Chanakya policy instead of static policy on edge deviceChanakya · Argoverse-HD Xavier NXsAP: 7.8 -> 8.3Improved
learned policy instead of static FCOS policyChanakya with FCOS · Argoverse-HDsAP: 16.7 -> 20.7Improved
learned policy on V100 GPU with expanded decision spaceChanakya · Argoverse-HD V100sAP: 18.3 -> 27.0Improved
add tracker and enlarge decision space to 500 configurationsChanakya · Argoverse-HDsAP: +1.6 sAPImproved
drop one context feature (ablation)Chanakya · Argoverse-HDsAP: approx 1 sAPHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy