ABD-Net: Attentive but Diverse Person Re-Identification
This work improves person re-identification for surveillance and security applications, but it is incremental as it builds on existing attention mechanisms by adding diversity constraints.
The paper tackled the problem of person re-identification by addressing the lack of diversity in attention-based feature embeddings, which compromises retrieval performance, and proposed ABD-Net to integrate attention with diversity regularization, achieving state-of-the-art results on three benchmarks.
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.