Auto-reid: Searching For A Part-aware Convnet For Person Re-identification

Abstract

Prevailing deep convolutional neural networks (CNNs) for person re-IDentification (reID) are usually built upon ResNet or VGG backbones, which were originally designed for classification. Because reID is different from classification, the architecture should be modified accordingly. We propose to automatically search for a CNN architecture that is specifically suitable for the reID task. There are three aspects to be tackled. First, body structural information plays an important role in reID but it is not encoded in backbones. Second, Neural Architecture Search (NAS) automates the process of architecture design without human effort, but no existing NAS methods incorporate the structure information of input images. Third, reID is essentially a retrieval task but current NAS algorithms are merely designed for classification. To solve these problems, we propose a retrieval-based search algorithm over a specifically designed reID search space, named Auto-ReID. Our Auto-ReID enables the aut

Stats

• citations200
• S2 citations—
• github stars0
• HF likes0
• heat score17.27
• arxiv keyquan2019auto

Related papers

• Structured Deep Hashing With Convolutional Neural Networks For Fast Person Re-identification (2017)12.87
• Neural Feature Search For Rgb-infrared Person Re-identification (2021)17.58
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61
• Ensemble Feature For Person Re-identification (2019)0.00
• Person Re-identification: Past, Present And Future (2016)0.00
• Svdnet For Pedestrian Retrieval (2017)20.96
• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71