Robust and Scalable Vehicle Re-Identification via Self-Supervision

Abstract

Many state-of-the-art solutions for vehicle re-identification (re-id) mostly focus on improving the accuracy on existing re-id benchmarks using additional annotated data. To balance the demands of accuracy, availability of annotated data, and computational efficiency, we propose a simple yet effective hybrid solution empowered by self-supervised learning which is free of intricate and computationally-demanding add-on attention modules often seen in state-of-the-art approaches. Through extensive experimentation, we show our approach, termed Self-Supervised and Boosted VEhicle Re-Identification (SSBVER), is on par with state-of-the-art alternatives in terms of accuracy without introducing any additional overhead during deployment. Additionally, we show that our approach, generalizes to different backbone architectures which accommodates various resource constraints and consistently results in a significant accuracy boost. Our code is available at https://github.com/Pirazh/SSBVER.