# RedunCut: Measurement-Driven Sampling and Accuracy Performance Modeling for Low-Cost Live Video Analytics

arXiv: https://arxiv.org/abs/2512.24386 · HTML: https://mlsanity.com/paper/2512.24386/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 47 of its 111 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Similarity of Neural Network Models: A Survey of Functional and Representational Measures](https://mlsanity.com/paper/2305.06329/) (2023)
- [Accelerating Distributed MoE Training and Inference with Lina](https://mlsanity.com/paper/2210.17223/) (2022)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [Vision Meets Drones: A Challenge](https://mlsanity.com/paper/1804.07437/) (2018)
- [STEP: Segmenting and Tracking Every Pixel](https://mlsanity.com/paper/2102.11859/) (2021)
- [Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers](https://mlsanity.com/paper/2012.10557/) (2020)
- [IDK Cascades: Fast Deep Learning by Learning not to Overthink](https://mlsanity.com/paper/1706.00885/) (2017)
- [Focus: Querying Large Video Datasets with Low Latency and Low Cost](https://mlsanity.com/paper/1801.03493/) (2018)
- [MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection](https://mlsanity.com/paper/2012.00914/) (2020)
- [Scaling Video Analytics on Constrained Edge Nodes](https://mlsanity.com/paper/1905.13536/) (2019)
- [Rafiki: Machine Learning as an Analytics Service System](https://mlsanity.com/paper/1804.06087/) (2018)

## Abstract (arXiv)

Live video analytics (LVA) runs continuously across massive camera fleets, but inference cost with modern vision models remains high. To address this, dynamic model size selection (DMSS) is an attractive approach: it is content-aware but treats models as black boxes, and could potentially reduce cost by up to 10x without model retraining or modification. Without ground truth labels at runtime, we observe that DMSS methods use two stages per segment: (i) sampling a few models to calculate prediction statistics (e.g., confidences), then (ii) selection of the model size from those statistics. Prior systems fail to generalize to diverse workloads, particularly to mobile videos and lower accuracy targets. We identify that the failure modes stem from inefficient sampling whose cost exceeds its benefit, and inaccurate per-segment accuracy prediction. In this work, we present RedunCut, a new DMSS system that addresses both: It uses a measurement-driven planner that estimates the cost-benefit tradeoff of sampling, and a lightweight, data-driven performance model to improve accuracy prediction. Across road-vehicle, drone, and surveillance videos and multiple model families and tasks, RedunCut reduces compute cost by 14-62% at fixed accuracy and remains robust to limited historical data and to drift.