为弱设备设计的渐进式图像压缩，支持部分数据时仍可准确推理。
LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks
- 按图像内容优先传输关键信息，实现渐进式编码。
- 在有限带宽下，比当前最优方法准确率提升14.01个百分点。
- 适合远程低带宽场景，如物联网终端和窄带网络部署。
物联网设备硬件能力有限，常部署于偏远地区。因此，先进视觉模型超出其处理与存储能力，需将任务卸载至云端。然而，偏远地区多依赖低功耗广域网（LPWAN），其带宽有限、丢包率高、信道周期极短，导致时间敏感的推理任务难以快速完成。现有可部署于弱设备的方法生成非渐进式比特流，当云侧因带宽限制或丢包仅获得部分数据时，解码质量严重下降。本文提出LimitNet，一种专为极端弱设备与网络设计的渐进式、内容感知图像压缩模型。其轻量级渐进编码器根据图像内容优先传输关键数据，使云侧即使在数据不完整时也能进行有效推理。实验表明，相比当前最优方法，LimitNet在ImageNet1000上平均准确率提升14.01个百分点，在CIFAR100上提升18.01个百分点，在COCO上[email protected]提升0.1；同时在ImageNet1000、CIFAR100、COCO上分别节省61.24%、83.68%、42.25%带宽。在STM32F7（Cortex-M7）上，编码时间仅比固定质量的JPEG多4%。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。