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

2024-07-10

arXiv.org

AI Summary

To address the weak zero-shot generalization capability of vehicle re-identification (ReID) models on unseen target domains, this paper proposes a source-free, two-stage multi-expert knowledge adversarial and collaborative framework. First, a Spectral Transform-based Redundancy Elimination and Enhancement Module (STREAM) is designed to suppress domain-specific redundant information in source-domain images within the frequency domain. Second, a CLIP semantic prompt-guided multi-expert adversarial collaboration mechanism is introduced to stimulate fine-grained, complementary feature modeling. The method integrates spectral-domain transformation, prompt-driven feature fusion, and multi-expert contrastive learning, thereby overcoming limitations of conventional domain-invariant feature modeling. Extensive experiments demonstrate state-of-the-art performance across multiple cross-domain vehicle ReID benchmarks, achieving significant improvements in zero-shot identification accuracy.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Transportation

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Generalizable vehicle ReID across unknown domains
• Eliminating domain-related redundancy in source images
• Enhancing complementary feature representation for ReID

Innovation

• Two-stage MiKeCoCo method enhances feature representation
• STREAM module eliminates domain-related redundancy effectively
• CLIP semantics used for diversified prompt set creation