Small, Accurate, and Fast Vehicle Re-ID on the Edge: the SAFR Approach

01/24/2020
by   Abhijit Suprem, et al.
9

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

page 2

page 3

page 6

research
02/06/2020

Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention

Vehicle re-identification (re-id) is a fundamental problem for modern su...
research
09/22/2022

Google Coral-based edge computing person reidentification using human parsing combined with analytical method

Person reidentification (re-ID) is becoming one of the most significant ...
research
04/14/2020

VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification

One fundamental challenge of vehicle re-identification (re-id) is to lea...
research
05/16/2022

Scalable Vehicle Re-Identification via Self-Supervision

As Computer Vision technologies become more mature for intelligent trans...
research
11/18/2020

Viewpoint-aware Progressive Clustering for Unsupervised Vehicle Re-identification

Vehicle re-identification (Re-ID) is an active task due to its importanc...
research
03/10/2021

ES-Net: Erasing Salient Parts to Learn More in Re-Identification

As an instance-level recognition problem, re-identification (re-ID) requ...
research
03/22/2021

Tiny Transformers for Environmental Sound Classification at the Edge

With the growth of the Internet of Things and the rise of Big Data, data...

Please sign up or login with your details

Forgot password? Click here to reset