Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

Page view(s)
16
Checked on Oct 03, 2024
Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
Title:
Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
Journal Title:
AAAI 2023
DOI:
Publication Date:
07 February 2023
Citation:
11
Abstract:
VQA is an ambitious task aiming to answer any image-related question. However, in reality, it is hard to build such a system once for all since the needs of users are continuously updated, and the system has to implement new functions. Thus, Continual Learning (CL) ability is a must in developing advanced VQA systems. Recently, a pioneer work split a VQA dataset into disjoint answer sets to study this topic. However, CL on VQA involves not only the expansion of label sets (new Answer sets). It is crucial to study how to answer questions when deploying VQA systems to new environments (new Visual scenes) and how to answer questions requiring new functions (new Question types). Thus, we propose CLOVE, a benchmark for Continual Learning On Visual quEstion answering, which contains scene- and function-incremental settings for the two aforementioned CL scenarios. In terms of methodology, the main difference between CL on VQA and classification is that the former additionally involves expanding and preventing forgetting of reasoning mechanisms, while the latter focusing on class representation. Thus, we propose a real-data-free replay-based method tailored for CL on VQA, named Scene Graph as Prompt for Symbolic Replay. Using a piece of scene graph as a prompt, it replays pseudo scene graphs to represent the past image, along with correlated QA pair. A unified VQA model is also proposed to utilize the current and replayed data to enhance its QA ability. Finally, experimental results reveal the challenges inCLOVE and demonstrate the effectiveness of our method.
License type:
Publisher Copyright
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 - NRF Fellowship
Grant Reference no. : NRF-NRFF13-2021- 0008

This research / project is supported by the National University of Singapore - Start-Up Grant
Grant Reference no. : N.A
Description:
ISSN:
https://arxiv.org/abs/2208.12037
Files uploaded:

File Size Format Action
220812037pdf-safe.pdf 9.03 MB PDF Open