Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification

TL;DR

This paper introduces a multi-attention soft partition network for vehicle re-identification that effectively captures discriminative features across viewpoints, reduces noise in attention maps, and outperforms existing attention-based methods without relying on metadata.

Contribution

The proposed model employs a novel multi-soft attention mechanism combined with a noise reduction technique and channel-wise attention, enhancing vehicle re-identification accuracy without extra metadata.

Findings

Achieved state-of-the-art performance among attention-based methods.

Comparable results to metadata-based approaches on VehicleID and VERI-Wild datasets.

Effectively reduces noise in spatial attention maps.

Abstract

Vehicle re-identification helps in distinguishing between images of the same and other vehicles. It is a challenging process because of significant intra-instance differences between identical vehicles from different views and subtle inter-instance differences between similar vehicles. To solve this issue, researchers have extracted view-aware or part-specific features via spatial attention mechanisms, which usually result in noisy attention maps or otherwise require expensive additional annotation for metadata, such as key points, to improve the quality. Meanwhile, based on the researchers' insights, various handcrafted multi-attention architectures for specific viewpoints or vehicle parts have been proposed. However, this approach does not guarantee that the number and nature of attention branches will be optimal for real-world re-identification tasks. To address these problems, we proposed a new vehicle re-identification network based on a multiple soft attention mechanism for capturing various discriminative regions from different viewpoints more efficiently. Furthermore, this model can significantly reduce the noise in spatial attention maps by devising a new method for creating an attention map for insignificant regions and then excluding it from generating the final result. We also combined a channel-wise attention mechanism with a spatial attention mechanism for the efficient selection of important semantic attributes for vehicle re-identification. Our experiments showed that our proposed model achieved a state-of-the-art performance among the attention-based methods without metadata and was comparable to the approaches using metadata for the VehicleID and VERI-Wild datasets.