Neural Architecture Search for Joint Human Parsing and Pose Estimation

Human parsing and pose estimation are crucial for the understanding of human behaviors. Since these tasks are closely related, employing one unified model to perform two tasks simultaneously allows them to benefit from each other. However, since human parsing is a pixel-wise classification process w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / IEEE International Conference on Computer Vision S. 11365 - 11374
Hauptverfasser: Zeng, Dan, Huang, Yuhang, Bao, Qian, Zhang, Junjie, Su, Chi, Liu, Wu
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2021
Schlagworte:
Computer architecture
Correlation
Gestures and body pose
Network architecture
Pose estimation
Semantics
Training
Visualization
ISSN:2380-7504
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Human parsing and pose estimation are crucial for the understanding of human behaviors. Since these tasks are closely related, employing one unified model to perform two tasks simultaneously allows them to benefit from each other. However, since human parsing is a pixel-wise classification process while pose estimation is usually a regression task, it is non-trivial to extract discriminative features for both tasks while modeling their correlation in the joint learning fashion. Recent studies have shown that Neural Architecture Search (NAS) has the ability to allocate efficient feature connections for specific tasks automatically. With the spirit of NAS, we propose to search for an efficient network architecture (NPPNet) to tackle two tasks at the same time. On the one hand, to extract task-specific features for the two tasks and lay the foundation for the further searching of feature interaction, we propose to search their encoder-decoder architectures, respectively. On the other hand, to ensure two tasks fully communicate with each other, we propose to embed NAS units in both multi-scale feature interaction and high-level feature fusion to establish optimal connections between two tasks. Experimental results on both parsing and pose estimation benchmark datasets have demonstrated that the searched model achieves state-of-the-art performances on both tasks. 1
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.01119