The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification
This addresses the scalability issue in vehicle re-identification for applications like surveillance by reducing reliance on costly labeled data.
The paper tackles vehicle re-identification by proposing a self-supervised attention method to learn discriminative features without expensive annotations, achieving state-of-the-art improvements on multiple challenging datasets.
In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information. These re-id methods rely on expensive key-point labels, part annotations, and additional attributes including vehicle make, model, and color. Given the large number of vehicle re-id datasets with various levels of annotations, strongly-supervised methods are unable to scale across different domains. In this paper, we present Self-supervised Attention for Vehicle Re-identification (SAVER), a novel approach to effectively learn vehicle-specific discriminative features. Through extensive experimentation, we show that SAVER improves upon the state-of-the-art on challenging VeRi, VehicleID, Vehicle-1M and VERI-Wild datasets.