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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Global Noise Filtering (ablation) | continual VQA baseline (VQACL-like) · VQA v2 continual (standard test) | AP: 38.77 -> 41.75 | Improved |
| add Global Noise Filtering (ablation) | continual VQA baseline (VQACL-like) · VQA v2 continual (standard test) | AF: 2.90 -> 2.14 | Improved |
| add Adaptive Memory Allocation (ablation) | continual VQA baseline (VQACL-like) · VQA v2 continual (standard test) | AP: 38.77 -> 40.97 | Improved |
| add Adaptive Memory Allocation (ablation) | continual VQA baseline (VQACL-like) · VQA v2 continual (standard test) | AF: 2.90 -> 2.34 | Improved |
| combine GonF and AMA (ablation) | MacVQA · VQA v2 continual (standard test) | AP: 41.75 -> 43.38 | Improved |
| combine GonF and AMA (ablation) | MacVQA · VQA v2 continual (standard test) | AF: 2.14 -> 2.32 | Mixed |
| use max-similarity instead of random prototype selection (ablation) | MacVQA · VQA v2 continual (standard test) | AP: 40.29 -> 43.38 | Improved |
| use max-similarity instead of random prototype selection (ablation) | MacVQA · VQA v2 continual (novel composition test) | AP: 41.25 -> 42.53 | Improved |
| use max-similarity instead of random prototype selection (ablation) | ProtoGroup · VQA v2 continual (standard test) | AP: 37.22 -> 39.81 | Improved |
| use MacVQA instead of best baseline | VL-T5 continual VQA · VQA v2 continual (novel composition test) | AP: 40.00 -> 42.53 | Improved |
Closest papers by meaning
- VQACL: A Novel Visual Question Answering Continual Learning Setting (CVPR 2023 · similarity 0.94)
- Re-evaluating Continual VQA: Toward Fair and Robust Evaluation for Multimodal Continual Learning (CVPR 2026 · similarity 0.94)
- Overcoming Dual Drift for Continual Long-Tailed Visual Question Answering (ICCV 2025 · similarity 0.93)
- AVQACL: A Novel Benchmark for Audio-Visual Question Answering Continual Learning (CVPR 2025 · similarity 0.92)
- CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering (CVPR 2025 · similarity 0.91)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.90)
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.
