IAB-Net: Informative and Attention Based Person Re-Identification

Abstract

This paper proposes Informative Attention Based IAB Network, a advance framework that unifieds multiple attention modules by preserving localized and global contextual information so that the model can learn most informative, representative and discriminative features. Specifically, we have also introduced Channel and Spatial Attention (CASA) Network that consists on a pair of attention modules named as Channel Attention Module and Spatial Attention Module. Channel attention module and spatial attention module primarily focusing on channel aggregation, spatial dimension and position awareness, respectively. In our proposed pipeline, we have used this pair after each convolutional block of ResNet-50, that significantly boost the performance and representation power of network. By using this new lightweight backbone with orthogonality constraint to enforce diversity on both hidden activation and weights and along with attention modules, our experiments on different popular benchmarks i.e Market-1501 and DukeMTMC-reID have achieved state-of-the-art performance and we confirm that our framework manifests harmonious refinement in detection and classification. The code is publicly available at this link https://github.com/faize5/IAB-Net.