HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
This work addresses the challenge of pedestrian analysis for security-centric computer vision systems, representing an incremental improvement with a novel attention mechanism.
The authors tackled the problem of learning comprehensive features for pedestrian analysis in fine-grained tasks by proposing HydraPlus-Net, an attention-based deep neural network that multi-directionally feeds multi-level attention maps to different feature layers, resulting in outperforming state-of-the-art methods on pedestrian attribute recognition and person re-identification across various datasets.
Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attention-based deep neural network, named as HydraPlus-Net (HP-net), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person re-identification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-the-art methods on various datasets.