Small, Accurate, and Fast Vehicle Re-ID on the Edge: the SAFR Approach
share
We propose a Small, Accurate, and Fast Re-ID (SAFR) design for flexible vehicle re-id under a variety of compute environments such as cloud, mobile, edge, or embedded devices by only changing the re-id model backbone. Through best-fit design choices, feature extraction, training tricks, global attention, and local attention, we create a reid model design that optimizes multi-dimensionally along model size, speed, accuracy for deployment under various memory and compute constraints. We present several variations of our flexible SAFR model: SAFR-Large for cloud-type environments with large compute resources, SAFR-Small for mobile devices with some compute constraints, and SAFR-Micro for edge devices with severe memory compute constraints. SAFR-Large delivers state-of-the-art results with mAP 81.34 on the VeRi-776 vehicle re-id dataset (15 drop in performance (mAP 77.14 on VeRi-776) for over 60 150 accuracy (mAP 75.80 on VeRi-776) for 95 to SAFR-Large.
READ FULL TEXT