RAM: A Region-Aware Deep Model for Vehicle Re-Identification

TL;DR

This paper introduces RAM, a deep learning model that enhances vehicle re-identification by combining global features with local region features, improving discrimination among similar vehicles.

Contribution

The paper proposes a novel Region-Aware deep Model (RAM) that extracts and fuses global and local regional features for more accurate vehicle Re-ID.

Findings

Achieves promising performance on VeRi and VehicleID datasets.

Outperforms recent methods in vehicle Re-ID accuracy.

Utilizes a joint learning algorithm with vehicle IDs, types, and colors.

Abstract

Previous works on vehicle Re-ID mainly focus on extracting global features and learning distance metrics. Because some vehicles commonly share same model and maker, it is hard to distinguish them based on their global appearances. Compared with the global appearance, local regions such as decorations and inspection stickers attached to the windshield, may be more distinctive for vehicle Re-ID. To embed the detailed visual cues in those local regions, we propose a Region-Aware deep Model (RAM). Specifically, in addition to extracting global features, RAM also extracts features from a series of local regions. As each local region conveys more distinctive visual cues, RAM encourages the deep model to learn discriminative features. We also introduce a novel learning algorithm to jointly use vehicle IDs, types/models, and colors to train the RAM. This strategy fuses more cues for training and results in more discriminative global and regional features. We evaluate our methods on two large-scale vehicle Re-ID datasets, i.e., VeRi and VehicleID. Experimental results show our methods achieve promising performance in comparison with recent works.