Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)

ECCV 2018  ·  Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, Shengjin Wang ·

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 similar to other parts. RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency. Experiment confirms that RPP allows PCB to gain another round of performance boost. For instance, on the Market-1501 dataset, we achieve (77.4+4.2)% mAP and (92.3+1.5)% rank-1 accuracy, surpassing the state of the art by a large margin.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Person Re-Identification DukeMTMC-reID PCB (UP) Rank-1 81.8 # 55
mAP 66.1 # 60
Person Re-Identification DukeMTMC-reID PCB (RPP) Rank-1 83.3 # 53
mAP 69.2 # 55
Person Re-Identification Market-1501 PCB Rank-1 92.3 # 63
mAP 77.4 # 72
Person Re-Identification Market-1501 PCB + RPP Rank-1 93.8 # 56
mAP 81.6 # 67
Person Re-Identification Market-1501-C PCB Rank-1 34.93 # 7
mAP 12.72 # 7
mINP 0.41 # 6
Person Re-Identification UAV-Human PCB mAP 61.05 # 3
Rank-1 62.19 # 3
Rank-5 83.90 # 3