Learning from the scene and borrowing from the rich: tackling the long tail in scene graph generation

Tao He, Lianli Gao, Jingkuan Song, Jianfei Cai, Yuan-Fang Li

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Despite the huge progress in scene graph generation in recent years, its long-tail distribution in object relationships remains a challenging and pestering issue. Existing methods largely rely on either external knowledge or statistical bias information to alleviate this problem. In this paper, we tackle this issue from another two aspects: (1) scene-object interaction aiming at learning specific knowledge from a scene via an additive attention mechanism; and (2) long-tail knowledge transfer which tries to transfer the rich knowledge learned from the head into the tail. Extensive experiments on the benchmark dataset Visual Genome on three tasks demonstrate that our method outperforms current state-of-the-art competitors. Our source code is available at https://github.com/htlsn/issg.
Original languageEnglish
Title of host publicationProceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
EditorsChristian Bessiere
Place of PublicationMarina del Rey CA USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Pages587-593
Number of pages7
ISBN (Electronic)9780999241165
DOIs
Publication statusPublished - 2020
EventInternational Joint Conference on Artificial Intelligence 2020 - Yokohama, Japan
Duration: 1 Jan 20213 Jan 2021
Conference number: 29th
https://www.ijcai.org/Proceedings/2020/ (Proceedings)
https://ijcai20.org (Website)

Conference

ConferenceInternational Joint Conference on Artificial Intelligence 2020
Abbreviated titleIJCAI 2020
CountryJapan
CityYokohama
Period1/01/213/01/21
Internet address

Keywords

  • Computer Vision
  • Recognition
  • Detection
  • Categorization
  • Indexing
  • Matching
  • Retrieval
  • Semantic Interpretation
  • Machine Learning
  • Deep Learning

Cite this

He, T., Gao, L., Song, J., Cai, J., & Li, Y-F. (2020). Learning from the scene and borrowing from the rich: tackling the long tail in scene graph generation. In C. Bessiere (Ed.), Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (pp. 587-593). Association for the Advancement of Artificial Intelligence (AAAI). https://doi.org/10.24963/ijcai.2020/82