AI Paper Atlas

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

MacVQA: Adaptive Memory Allocation and Global Noise Filtering for Continual Visual Question Answering

Zhifei Li, Yiran Wang, Chenyi Xiong, Yujing Xia, Xiaoju Hou, Yue Zhao, Miao Zhang, Kui Xiao, Bing Yang

AAAI 2026 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 1 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 Global Noise Filtering (ablation)continual VQA baseline (VQACL-like) · VQA v2 continual (standard test)AP: 38.77 -> 41.75Improved
add Global Noise Filtering (ablation)continual VQA baseline (VQACL-like) · VQA v2 continual (standard test)AF: 2.90 -> 2.14Improved
add Adaptive Memory Allocation (ablation)continual VQA baseline (VQACL-like) · VQA v2 continual (standard test)AP: 38.77 -> 40.97Improved
add Adaptive Memory Allocation (ablation)continual VQA baseline (VQACL-like) · VQA v2 continual (standard test)AF: 2.90 -> 2.34Improved
combine GonF and AMA (ablation)MacVQA · VQA v2 continual (standard test)AP: 41.75 -> 43.38Improved
combine GonF and AMA (ablation)MacVQA · VQA v2 continual (standard test)AF: 2.14 -> 2.32Mixed
use max-similarity instead of random prototype selection (ablation)MacVQA · VQA v2 continual (standard test)AP: 40.29 -> 43.38Improved
use max-similarity instead of random prototype selection (ablation)MacVQA · VQA v2 continual (novel composition test)AP: 41.25 -> 42.53Improved
use max-similarity instead of random prototype selection (ablation)ProtoGroup · VQA v2 continual (standard test)AP: 37.22 -> 39.81Improved
use MacVQA instead of best baselineVL-T5 continual VQA · VQA v2 continual (novel composition test)AP: 40.00 -> 42.53Improved

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