Feature Compression for Rate Constrained Object Detection on the Edge
Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual analytics neural networks. An emerging approach to solve this problem is to offload the computation of these neural networks to computing resources at an edge server. Efficient computation offloading requires optimizing the trade-off between multiple objectives including compressed data rate, analytics performance, and computation speed. In this work, we consider a "split computation" system to offload a part of the computation of the YOLO object detection model. We propose a learnable feature compression approach to compress the intermediate YOLO features with light-weight computation. We train the feature compression and decompression module together with the YOLO model to optimize the object detection accuracy under a rate constraint. Compared to baseline methods that apply either standard image compression or learned image compression at the mobile and perform image decompression and YOLO at the edge, the proposed system achieves higher detection accuracy at the low to medium rate range. Furthermore, the proposed system requires substantially lower computation time on the mobile device with CPU only.
Code (0)
등록된 구현이 없습니다.
Tasks
CPUFeature CompressionImage Compressionobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AHC: Meta-Learned Adaptive Compression for Continual Object Detection on Memory-Constrained Microcontrollers
Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression …
Object DetectionExtended Bit-Plane Compression for Convolutional Neural Network Accelerators
After the tremendous success of convolutional neural networks in image classification, object detection, speech recognition, etc., there is now rising demand for deployment of these compute-intensive ML models on tightly…
image-classificationImage Classificationobject-detectionObject Detection+2Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performance
Deep learning has made great strides for object detection in images. The detection accuracy and computational cost of object detection depend on the spatial resolution of an image, which may be constrained by both the ca…
Objectobject-detectionObject DetectionAn Embedded Deep Learning Object Detection Model For Traffic In Asian Countries
Deep learning-based object detection algorithms have been developed through extensive research and achieved impressive performance. However, due to the heavy computation of deep convolutional neural networks, it is not s…
Deep LearningModel CompressionObjectobject-detection+1Object Detection in the DCT Domain: is Luminance the Solution?
Object detection in images has reached unprecedented performances. The state-of-the-art methods rely on deep architectures that extract salient features and predict bounding boxes enclosing the objects of interest. These…
Objectobject-detectionObject Detection