Beyond Part Models: Person Retrieval With Refined Part Pooling (and A Strong Convolutional Baseline)

Abstract

Employing part-level features for pedestrian image description offers fine-grained information and has been verified as beneficial for person retrieval in very recent literature. A prerequisite of part discovery is that each part should be well located. Instead of using external cues, e.g., pose estimation, to directly locate parts, this paper lays emphasis on the content consistency within each part. Specifically, we target at learning discriminative part-informed features for person retrieval and make two contributions. (i) A network named Part-based Convolutional Baseline (PCB). Given an image input, it outputs a convolutional descriptor consisting of several part-level features. With a uniform partition strategy, PCB achieves competitive results with the state-of-the-art methods, proving itself as a strong convolutional baseline for person retrieval. (ii) A refined part pooling (RPP) method. Uniform partition inevitably incurs outliers in each part, which are in fact more simil

Stats

• citations1739
• S2 citations—
• github stars0
• HF likes0
• heat score24.30
• arxiv keysun2017beyond

Related papers

• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• TIPCB: A Simple But Effective Part-based Convolutional Baseline For Text-based Person Search (2021)20.24
• Pose Invariant Embedding For Deep Person Re-identification (2017)19.34
• Part-aligned Bilinear Representations For Person Re-identification (2018)19.30
• Body Part-based Representation Learning For Occluded Person Re-identification (2022)21.32
• Decoupled And Memory-reinforced Networks: Towards Effective Feature Learning For One-step Person Search (2021)12.25
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Unsupervised Part Learning For Visual Recognition (2017)8.82