CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification

TL;DR

This paper introduces CA-Jaccard, a camera-aware distance metric for person re-identification that improves neighbor reliability by leveraging camera information, leading to better retrieval accuracy with low computational cost.

Contribution

The paper proposes a novel camera-aware Jaccard distance that incorporates camera information into neighbor selection and weighting, enhancing reliability in person re-ID.

Findings

CA-Jaccard improves re-ID accuracy across multiple datasets.

The method effectively leverages camera information for neighbor reliability.

Experiments show CA-Jaccard outperforms existing metrics with low computational overhead.

Abstract

Person re-identification (re-ID) is a challenging task that aims to learn discriminative features for person retrieval. In person re-ID, Jaccard distance is a widely used distance metric, especially in re-ranking and clustering scenarios. However, we discover that camera variation has a significant negative impact on the reliability of Jaccard distance. In particular, Jaccard distance calculates the distance based on the overlap of relevant neighbors. Due to camera variation, intra-camera samples dominate the relevant neighbors, which reduces the reliability of the neighbors by introducing intra-camera negative samples and excluding inter-camera positive samples. To overcome this problem, we propose a novel camera-aware Jaccard (CA-Jaccard) distance that leverages camera information to enhance the reliability of Jaccard distance. Specifically, we design camera-aware k-reciprocal nearest neighbors (CKRNNs) to find k-reciprocal nearest neighbors on the intra-camera and inter-camera ranking lists, which improves the reliability of relevant neighbors and guarantees the contribution of inter-camera samples in the overlap. Moreover, we propose a camera-aware local query expansion (CLQE) to mine reliable samples in relevant neighbors by exploiting camera variation as a strong constraint and assign these samples higher weights in overlap, further improving the reliability. Our CA-Jaccard distance is simple yet effective and can serve as a general distance metric for person re-ID methods with high reliability and low computational cost. Extensive experiments demonstrate the effectiveness of our method.