# Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems

arXiv: https://arxiv.org/abs/2201.00063 · HTML: https://mlsanity.com/paper/2201.00063/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 31 Dec 2021.

## Builds on (most cited first, 19 of 19)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1901.06032/) (2019)
- [Soft Weight-Sharing for Neural Network Compression](https://mlsanity.com/paper/1702.04008/) (2017)
- [Deep Neural Network Compression for Aircraft Collision Avoidance Systems](https://mlsanity.com/paper/1810.04240/) (2018)
- [NoScope: Optimizing Neural Network Queries over Video at Scale](https://mlsanity.com/paper/1703.02529/) (2017)
- [A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation](https://mlsanity.com/paper/1707.01202/) (2017)
- [Deep Neural Network Compression with Single and Multiple Level Quantization](https://mlsanity.com/paper/1803.03289/) (2018)
- [Coreset-Based Neural Network Compression](https://mlsanity.com/paper/1807.09810/) (2018)
- [DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework](https://mlsanity.com/paper/1803.05788/) (2018)
- [Accurate and Compact Convolutional Neural Networks with Trained Binarization](https://mlsanity.com/paper/1909.11366/) (2019)
- [Universal Deep Neural Network Compression](https://mlsanity.com/paper/1802.02271/) (2018)
- [WedgeChain: A Trusted Edge-Cloud Store With Asynchronous (Lazy) Trust](https://mlsanity.com/paper/2012.02258/) (2020)

## Built on by (most cited first, 1 of 1)

- [Efficient Dynamic Clustering: Capturing Patterns from Historical Cluster Evolution](https://mlsanity.com/paper/2203.00812/) (2022)

## Abstract (arXiv)

Emerging edge applications require both a fast response latency and complex processing. This is infeasible without expensive hardware that can process complex operations -- such as object detection -- within a short time. Many approach this problem by addressing the complexity of the models -- via model compression, pruning and quantization -- or compressing the input. In this paper, we propose a different perspective when addressing the performance challenges. Croesus is a multi-stage approach to edge-cloud systems that provides the ability to find the balance between accuracy and performance. Croesus consists of two stages (that can be generalized to multiple stages): an initial and a final stage. The initial stage performs the computation in real-time using approximate/best-effort computation at the edge. The final stage performs the full computation at the cloud, and uses the results to correct any errors made at the initial stage. In this paper, we demonstrate the implications of such an approach on a video analytics use-case and show how multi-stage processing yields a better balance between accuracy and performance. Moreover, we study the safety of multi-stage transactions via two proposals: multi-stage serializability (MS-SR) and multi-stage invariant confluence with Apologies (MS-IA).