Scout: Open-World Species Recognition on the Edge

2026-09-19

AI Summary

研究解决了边缘设备上开放世界物种识别问题，通过间歇性调用云端视觉-语言模型来训练紧凑的边缘模型，实现资源高效利用。

Abstract

Large vision-language models (VLMs) enable recognition beyond a fixed class set, but their computational demands prevent them from running on many edge devices. Cloud offload makes this capability accessible, but sending every image consumes scarce bandwidth and communication energy. We ask how to bring the open-world recognition capability of VLMs to the edge while operating within tight compute, energy, and bandwidth budgets. Wildlife monitoring provides a natural setting for exploring this question because camera traps encounter species not known at deployment. We present Scout, an autonomous open-world recognition system that invokes a cloud VLM intermittently to teach new classes to a compact edge model. Given only the deployment location and empty site frames, Scout autonomously turns each species identified by the VLM into persistent, site-conditioned recognition capability in a resource-efficient edge model, without a predefined species list, human labeling, or manual tuning. Across 30 camera-trap deployments in three regions on an NVIDIA Jetson Orin Nano, the accuracy of Scout remains within 0.1-2.5% of a model given a predefined species list. On species outside its initial class set, Scout achieves 53.7-59.1% accuracy, compared with 56.5-65.1% for full cloud offload, while using 59-71% less deployment energy.

Problem

• open-world recognition
• edge devices
• bandwidth
• energy budget
• wildlife monitoring

Innovation

• Open-World Recognition
• Edge Computing
• Visual-Language Models
• Autonomous Learning
• Wildlife Monitoring