ABD-Net: Attentive but Diverse Person Re-Identification

TL;DR

ABD-Net enhances person re-identification by integrating attention mechanisms with diversity regularization, leading to more discriminative features and improved performance across multiple benchmarks.

Contribution

The paper introduces a novel ABD-Net that combines attention modules with a new orthogonality constraint to enforce diversity in feature embeddings.

Findings

ABD-Net outperforms state-of-the-art methods on three benchmarks.

Attention and diversity regularization each contribute to performance improvements.

Orthogonality constraints improve feature discriminability.

Abstract

Attention mechanism has been shown to be effective for person re-identification (Re-ID). However, the learned attentive feature embeddings which are often not naturally diverse nor uncorrelated, will compromise the retrieval performance based on the Euclidean distance. We advocate that enforcing diversity could greatly complement the power of attention. To this end, we propose an Attentive but Diverse Network (ABD-Net), which seamlessly integrates attention modules and diversity regularization throughout the entire network, to learn features that are representative, robust, and more discriminative. Specifically, we introduce a pair of complementary attention modules, focusing on channel aggregation and position awareness, respectively. Furthermore, a new efficient form of orthogonality constraint is derived to enforce orthogonality on both hidden activations and weights. Through careful ablation studies, we verify that the proposed attentive and diverse terms each contributes to the performance gains of ABD-Net. On three popular benchmarks, ABD-Net consistently outperforms existing state-of-the-art methods.