# Arena: A Patch-of-Interest ViT Inference Acceleration System for Edge-Assisted Video Analytics

arXiv: https://arxiv.org/abs/2404.09245 · HTML: https://mlsanity.com/paper/2404.09245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Token pruning and merging for ViTs, one of 12 directions in Efficient LLM inference and serving.
- Builds on 31 of its 70 references that are in the map.
- First posted on arXiv 14 Apr 2024.

## Placed in

- Efficient LLM inference and serving / [Token pruning and merging for ViTs](https://mlsanity.com/inference/token-pruning-and-merging-for-vits/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [Deep Feature Flow for Video Recognition](https://mlsanity.com/paper/1611.07715/) (2016)
- [Token Fusion: Bridging the Gap between Token Pruning and Token Merging](https://mlsanity.com/paper/2312.01026/) (2023)
- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers](https://mlsanity.com/paper/2304.10716/) (2023)
- [Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers](https://mlsanity.com/paper/2211.11315/) (2022)
- [V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection](https://mlsanity.com/paper/2308.04409/) (2023)
- [The 6th AI City Challenge](https://mlsanity.com/paper/2204.10380/) (2022)
- [Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator](https://mlsanity.com/paper/2108.12858/) (2021)
- [Turbo: Opportunistic Enhancement for Edge Video Analytics](https://mlsanity.com/paper/2207.00172/) (2022)
- [Taming Detection Transformers for Medical Object Detection](https://mlsanity.com/paper/2306.15472/) (2023)

## Abstract (arXiv)

The advent of edge computing has made real-time intelligent video analytics feasible. Previous works, based on traditional model architecture (e.g., CNN, RNN, etc.), employ various strategies to filter out non-region-of-interest content to minimize bandwidth and computation consumption but show inferior performance in adverse environments. Recently, visual foundation models based on transformers have shown great performance in adverse environments due to their amazing generalization capability. However, they require a large amount of computation power, which limits their applications in real-time intelligent video analytics. In this paper, we find visual foundation models like Vision Transformer (ViT) also have a dedicated acceleration mechanism for video analytics. To this end, we introduce Arena, an end-to-end edge-assisted video inference acceleration system based on ViT. We leverage the capability of ViT that can be accelerated through token pruning by only offloading and feeding Patches-of-Interest to the downstream models. Additionally, we design an adaptive keyframe inference switching algorithm tailored to different videos, capable of adapting to the current video content to jointly optimize accuracy and bandwidth. Through extensive experiments, our findings reveal that Arena can boost inference speeds by up to 1.58(×) and 1.82(×) on average while consuming only 47% and 31% of the bandwidth, respectively, all with high inference accuracy.