Adaptive Visual Scene Understanding: Incremental Scene Graph Generation

Page view(s)
34
Checked on Apr 09, 2025
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
Title:
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
Journal Title:
NeurIPS 2024
Keywords:
Publication Date:
02 October 2023
Citation:
Khandelwal, N., Liu, X. and Zhang, M., 2023. Adaptive Visual Scene Understanding: Incremental Scene Graph Generation. arXiv preprint arXiv:2310.01636.
Abstract:
Scene graph generation (SGG) analyzes images to extract meaningful information about objects and their relationships. In the dynamic visual world, it is crucial for AI systems to continuously detect new objects and establish their relationships with existing ones. Recently, numerous studies have focused on continual learning within the domains of object detection and image recognition. However, a limited amount of research focuses on a more challenging continual learning problem in SGG. This increased difficulty arises from the intricate interactions and dynamic relationships among objects, and their associated contexts. Thus, in continual learning, SGG models are often required to expand, modify, retain, and reason scene graphs within the process of adaptive visual scene understanding. To systematically explore Continual Scene Graph Generation (CSEGG), we present a comprehensive benchmark comprising three learning regimes: relationship incremental, scene incremental, and relationship generalization. Moreover, we introduce a “Replays via Analysis by Synthesis" method named RAS. This approach leverages the scene graphs, decomposes and re-composes them to represent different scenes, and replays the synthesized scenes based on these compositional scene graphs. The replayed synthesized scenes act as a means to practice and refine proficiency in SGG in known and unknown environments. Our experimental results not only highlight the challenges of directly combining existing continual learning methods with SGG backbones but also demonstrate the effectiveness of our proposed approach, enhancing CSEGG efficiency while simultaneously preserving privacy and memory usage. All data and source code are publicly available here.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG2-RP-2021-025

This research / project is supported by the National Research Foundation - NRFF Award
Grant Reference no. : NRF-NRFF15-2023- 0001

This research / project is supported by the Agency for Science, Technology, and Research (A*STAR) - Start-up Grant
Grant Reference no. :

This research / project is supported by the Nanyang Technological University - Start-up Grant
Grant Reference no. :

This research / project is supported by the Agency for Science, Technology, and Research (A*STAR) - Center for Frontier AI Research (CFAR) Early Career Investigatorship
Grant Reference no. :
Description:
ISBN:
arXiv:2310.01636
Files uploaded:

File Size Format Action
231001636v4.pdf 39.95 MB PDF Open