AI Paper Atlas

Research map / Continual learning / Online and replay-based

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

Stan Weixian Lei, Difei Gao, Jay Zhangjie Wu, Yuxuan Wang, Wei Liu, Mengmi Zhang, Mike Zheng Shou

AAAI 2023 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 32 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use symbolic replay of scene graphs and associated QA pairs instead of no replayUniVQA on CLOVE-scene · CLOVE-scene (six task orders)average accuracy (%): 26.92 -> 33.05Improved
Use symbolic replay of scene graphs and associated QA pairs instead of no replayUniVQA on CLOVE-function · CLOVE-function (six task orders)average accuracy (%): 26.16 -> 42.01Improved
Use symbolic replay rather than VQG image-and-answer replayUniVQA on CLOVE-scene · CLOVE-scene (six task orders)average accuracy (%): 29.19 -> 33.05Improved
Use symbolic replay rather than VQG image-and-answer replayUniVQA on CLOVE-function · CLOVE-function (six task orders)average accuracy (%): 31.36 -> 42.01Improved
Replace random SG prompts with stored ground-truth SG prompts (ablation)SGP · CLOVE-scene (γ=0.9)average accuracy (%): 32.08 -> 35.09Improved
Replace random SG prompts with stored ground-truth SG prompts (ablation)SGP · CLOVE-function (γ=0.9)average accuracy (%): 44.21 -> 47.01Improved
Add scene-graph replay to QA-pair replay (ablation)SGP · CLOVE-scene (γ=0.9)average accuracy (%): 29.52 -> 32.08Improved
Add scene-graph replay to QA-pair replay (ablation)SGP · CLOVE-function (γ=0.9)average accuracy (%): 40.24 -> 44.21Improved
Use symbolic scene-graph replay instead of stored real-data replayUniVQA on CLOVE-scene · CLOVE-scene (six task orders)average accuracy (%): 37.19 -> 33.05Hurt
Use symbolic scene-graph replay instead of stored real-data replayUniVQA on CLOVE-function · CLOVE-function (six task orders)average accuracy (%): 41.84 -> 42.01No clear effect
Train SRM with only 1% of scene-graph annotations (ablation)SGP on CLOVE-function-oarlks · CLOVE-functionaverage accuracy (%): +4.9%Improved
Increase replay amount beyond γ=0.7 (ablation)UniVQA on CLOVE-function · CLOVE-functionaverage accuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy