2023 Low-Power Computer Vision Challenge (LPCVC) Summary
Not on the map. Why?
Abstract (arXiv)
This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC). Since 2015, LPCVC has been an international competition devoted to tackling the challenge of computer vision (CV) on edge devices. Most CV researchers focus on improving accuracy, at the expense of ever-growing sizes of machine models. LPCVC balances accuracy with resource requirements. Winners must achieve high accuracy with short execution time when their CV solutions run on an embedded device, such as Raspberry PI or Nvidia Jetson Nano. The vision problem for 2023 LPCVC is segmentation of images acquired by Unmanned Aerial Vehicles (UAVs, also called drones) after disasters. The 2023 LPCVC attracted 60 international teams that submitted 676 solutions during the submission window of one month. This article explains the setup of the competition and highlights the winners' methods that improve accuracy and shorten execution time.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 44 references that are in the map. First posted on arXiv 11 Mar 2024.
Builds on
19 of 44 references.
References · 19
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
- 2016Pyramid Scene Parsing Networkcited by 2,472
- 2021Dynamic Neural Networks: A Surveycited by 405
- 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
- 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
- 2022TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentationcited by 82
- 2021Adaptive Focus for Efficient Video Recognitioncited by 76
- 2023Adaptive Rotated Convolution for Rotated Object Detectioncited by 51
- 2019AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Ratescited by 49
- 2023Rank-DETR for High Quality Object Detectioncited by 49
- 2022Learning to Weight Samples for Dynamic Early-exiting Networkscited by 44
- 2022Glance and Focus Networks for Dynamic Visual Recognitioncited by 41
7 more
- 2020Real-time Semantic Segmentation with Fast Attentioncited by 36
- 2023Dynamic Perceiver for Efficient Visual Recognitioncited by 33
- 2023Latency-aware Unified Dynamic Networks for Efficient Image Recognitioncited by 26
- 2022Latency-aware Spatial-wise Dynamic Networkscited by 25
- 2022Fully Transformer Network for Change Detection of Remote Sensing Imagescited by 17
- 2023Fine-grained Recognition with Learnable Semantic Data Augmentationcited by 17
- 2023TransY-Net:Learning Fully Transformer Networks for Change Detection of Remote Sensing Imagescited by 13
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.