Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification

TL;DR

This paper introduces MiKeCoCo, a novel multi-expert approach leveraging CLIP and redundancy elimination to improve vehicle re-identification across unknown domains, achieving state-of-the-art results.

Contribution

It proposes a two-stage method combining redundancy elimination and multi-expert collaboration using CLIP to enhance generalizable vehicle ReID.

Findings

Achieves state-of-the-art performance on vehicle ReID benchmarks.

Effectively reduces domain-related redundancy in source images.

Enhances fine-grained feature discrimination for better identity recognition.

Abstract

Generalizable vehicle re-identification (ReID) seeks to develop models that can adapt to unknown target domains without the need for additional fine-tuning or retraining. Previous works have mainly focused on extracting domain-invariant features by aligning data distributions between source domains. However, interfered by the inherent domain-related redundancy in the source images, solely relying on common features is insufficient for accurately capturing the complementary features with lower occurrence probability and smaller energy. To solve this unique problem, we propose a two-stage Multi-expert Knowledge Confrontation and Collaboration (MiKeCoCo) method, which fully leverages the high-level semantics of Contrastive Language-Image Pretraining (CLIP) to obtain a diversified prompt set and achieve complementary feature representations. Specifically, this paper first designs a Spectrum-based Transformation for Redundancy Elimination and Augmentation Module (STREAM) through simple image preprocessing to obtain two types of image inputs for the training process. Since STREAM eliminates domain-related redundancy in source images, it enables the model to pay closer attention to the detailed prompt set that is crucial for distinguishing fine-grained vehicles. This learned prompt set related to the vehicle identity is then utilized to guide the comprehensive representation learning of complementary features for final knowledge fusion and identity recognition. Inspired by the unity principle, MiKeCoCo integrates the diverse evaluation ways of experts to ensure the accuracy and consistency of ReID. Extensive experimental results demonstrate that our method achieves state-of-the-art performance.