AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering

Imad Eddine Marouf, Enzo Tartaglione, Stéphane Lathuilière, Joost Van De Weijer

ICCV 2025 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 8 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
add attention consistency distillation to question-only replay (ablation)QUAD · VQAv2 (standard test)AP: 30.72 -> 39.25Improved
add attention consistency distillation to question-only replay (ablation)QUAD · NExT-QA (standard test)AP: 29.04 -> 31.70Improved
add question-only replay to attention distillation (ablation)QUAD · VQAv2 (standard test)AP: 13.34 -> 39.25Improved
add question-only replay to attention distillation (ablation)QUAD · NExT-QA (standard test)AP: 13.24 -> 31.70Improved
add attention distillation to question-only replay (ablation)QUAD · VQAv2 (standard test)Forgetting: 13.74 -> 4.91Improved
use cross-entropy on softmax attention instead of L1 on raw attention (ablation)QUAD · VQAv2 (standard test)AP: 34.56 -> 39.25Improved
use cross-entropy on softmax attention instead of L1 on raw attention (ablation)QUAD · NExT-QA (standard test)AP: 30.14 -> 31.70Improved
use cross-entropy attention distillation instead of asymmetric ReLU+L1 (ablation)QUAD · VQAv2 (standard test)AP: 38.15 -> 39.25Improved
use cross-entropy attention distillation instead of asymmetric ReLU+L1 (ablation)QUAD · NExT-QA (standard test)Forgetting: 4.13 -> 2.91Improved
replace stored image-question pairs with question-only replay (no images)QUAD vs VQACL · VQAv2 (standard test)AP: 37.46 -> 39.25Improved
replace stored image-question pairs with question-only replay (no images)QUAD vs VQACL · NExT-QA (standard test)AP: 30.86 -> 31.70Mixed
question-only replay vs image storage on pretrained LLaVA-7BQUAD vs CL-MoE · VQAv2 (LLaVA-7B pretrained)AP: 52.96 -> 44.16Hurt

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