LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks
arXiv:2504.13736 · doi:10.1145/3643832.3661856
Abstract
IoT devices have limited hardware capabilities and are often deployed in remote areas. Consequently, advanced vision models surpass such devices' processing and storage capabilities, requiring offloading of such tasks to the cloud. However, remote areas often rely on LPWANs technology with limited bandwidth, high packet loss rates, and extremely low duty cycles, which makes fast offloading for time-sensitive inference challenging. Today's approaches, which are deployable on weak devices, generate a non-progressive bit stream, and therefore, their decoding quality suffers strongly when data is only partially available on the cloud at a deadline due to limited bandwidth or packet losses. In this paper, we introduce LimitNet, a progressive, content-aware image compression model designed for extremely weak devices and networks. LimitNet's lightweight progressive encoder prioritizes critical data during transmission based on the content of the image, which gives the cloud the opportunity to run inference even with partial data availability. Experimental results demonstrate that LimitNet, on average, compared to SOTA, achieves 14.01 p.p. (percentage point) higher accuracy on ImageNet1000, 18.01 pp on CIFAR100, and 0.1 higher [email protected] on COCO. Also, on average, LimitNet saves 61.24% bandwidth on ImageNet1000, 83.68% on CIFAR100, and 42.25% on the COCO dataset compared to SOTA, while it only has 4% more encoding time compared to JPEG (with a fixed quality) on STM32F7 (Cortex-M7).
This is the author's accepted manuscript. The Version of Record is available at: https://doi.org/10.1145/3643832.3661856
References in corpus (11)
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
- SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
- MCUNet: Tiny Deep Learning on IoT Devices
- Joint Device-Edge Inference over Wireless Links with Pruning
- Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
- Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
- Supervised Compression for Resource-Constrained Edge Computing Systems
- Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI
- DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device
- DRASIC: Distributed Recurrent Autoencoder for Scalable Image Compression