ABD-Net: Attentive but Diverse Person Re-Identification

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.

arXiv commentICCV2019

References in corpus (15)

• The NumPy array: a structure for efficient numerical computation
• In Defense of the Triplet Loss for Person Re-Identification
• Person Re-identification: Past, Present and Future
• Random Erasing Data Augmentation
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Representation Learning with Part Loss for Person Re-Identification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Deep Transfer Learning for Person Re-identification
• Dual Attention Network for Scene Segmentation
• Pose Invariant Embedding for Deep Person Re-identification
• Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
• Attention-Aware Compositional Network for Person Re-identification
• Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
• Generalized BackPropagation, Étude De Cas: Orthogonality
• Optimization on Submanifolds of Convolution Kernels in CNNs

Cited by in corpus (7)

• Learning to Disentangle Scenes for Person Re-identification
• HAT: Hierarchical Aggregation Transformers for Person Re-identification
• Learning to Optimize in Swarms
• Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
• Hierarchical Feature Embedding for Attribute Recognition
• Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
• Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification