EUVIMEDEUVIMED entdecken
Crossref

Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation

Jinghao Wang, Zhengyu Wen, Xiangtai Li, Zujin Guo, Jingkang Yang, Ziwei Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 10452-10465

DOI: 10.1109/tpami.2024.3442301 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Jinghao Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: Ministry of Education - Singapore, NTU NAP, RIE2020 Industry Alignment Fund Industry Collaboration Projects.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Panoptic Scene Graph (PSG) is a challenging task in Scene Graph Generation (SGG) that aims to create a more comprehensive scene graph representation using panoptic segmentation instead of boxes. Compared to SGG, PSG has several challenging problems: pixel-level segment outputs and full relationship exploration (It also considers thing and stuff relation). Thus, current PSG methods have limited performance, which hinders downstream tasks or applications. This work aims to design a novel and strong baseline for PSG. To achieve that, we first conduct an in-depth analysis to identify the bottleneck of the current PSG models, finding that inter-object pair-wise recall is a crucial factor that was ignored by previous PSG methods. Based on this and the recent query-based frameworks, we present a novel framework: Pair then Relation (Pair-Net), which uses a Pair Proposal Network (PPN) to learn and filter sparse pair-wise relationships between subjects and objects. Moreover, we also observed the sparse nature of object pairs for both. Motivated by this, we design a lightweight Matrix Learner within the PPN, which directly learns pair-wised relationships for pair proposal generation. Through extensive ablation and analysis, our approach significantly improves upon leveraging the segmenter solid baseline. Notably, our method achieves over 10% absolute gains compared to our baseline, PSGFormer.

Förderung

  • Ministry of Education - Singapore
  • NTU NAP
  • RIE2020 Industry Alignment Fund Industry Collaboration Projects

Zitieren

APA

Wang, J., Wen, Z., Li, X., Guo, Z., Yang, J., & Liu, Z. (2024). Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10452-10465. https://doi.org/10.1109/tpami.2024.3442301

Vancouver

Wang J, Wen Z, Li X, Guo Z, Yang J, Liu Z. Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):10452-10465. doi:10.1109/tpami.2024.3442301

BibTeX
@article{Wang2024,
  author = {Wang, Jinghao and Wen, Zhengyu and Li, Xiangtai and Guo, Zujin and Yang, Jingkang and Liu, Ziwei},
  title = {Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {10452--10465},
  doi = {10.1109/tpami.2024.3442301}
}
Kostenlos starten →