HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

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.

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract

Datasets


Introduced in the Paper:

PA-100K

Used in the Paper:

Market-1501 CUHK03 VIPeR PETA RAP
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Pedestrian Attribute Recognition PA-100K HP-net Accuracy 72.19% # 11
Pedestrian Attribute Recognition PETA HP-net Accuracy 76.13% # 6
Pedestrian Attribute Recognition RAP HP-net Accuracy 65.39% # 2

Methods


No methods listed for this paper. Add relevant methods here