Efficient Feature Compression for Edge-Cloud Systems
Optimizing computation in an edge-cloud system is an important yet challenging problem. In this paper, we consider a three-way trade-off between bit rate, classification accuracy, and encoding complexity in an edge-cloud image classification system. Our method includes a new training strategy and an efficient encoder architecture to improve the rate-accuracy performance. Our design can also be easily scaled according to different computation resources on the edge device, taking a step towards achieving a rate-accuracy-complexity (RAC) trade-off. Under various settings, our feature coding system consistently outperforms previous methods in terms of the RAC performance.
Code (1)
Tasks
ClassificationFeature Compressionimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Feature Compression for Cloud-Edge Multimodal 3D Object Detection
Machine vision systems, which can efficiently manage extensive visual perception tasks, are becoming increasingly popular in industrial production and daily life. Due to the challenge of simultaneously obtaining accurate…
3D Object Detection3D Object ReconstructionFeature Compressionobject-detection+2Codebook-Based Adaptive Feature Compression With Semantic Enhancement for Edge-Cloud Systems
Coding images for machines with minimal bitrate and strong analysis performance is key to effective edge-cloud systems. Several approaches deploy an image codec and perform analysis on the reconstructed image. Other meth…
SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference
Edge-cloud co-inference enables efficient deep neural network (DNN) deployment by splitting the architecture between an edge device and cloud server, crucial for resource-constraint edge devices. This approach requires b…
DecoderFeature CompressionDynaFilter: Cloud-driven Dynamic Filtering for Satellite Edge Intelligence
Modern satellite edge systems, including those performing remote sensing tasks such object detection and tracking, are characterized by severely limited bandwidth and intermittent connections, making continuous data tran…
Object DetectionHave We Scene It All? Scene Graph-Aware Deep Point Cloud Compression
Efficient transmission of 3D point cloud data is critical for advanced perception in centralized and decentralized multi-agent robotic systems, especially nowadays with the growing reliance on edge and cloud-based proces…
Point Clouds