Research map / Vision-language and multimodal / Visual question answering
Overcoming Language Priors in VQA via Decomposed Linguistic Representations
Chenchen Jing, Yuwei Wu, Xiaoxun Zhang, Yunde Jia, Qi Wu
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 decomposed linguistic representations (language attention + verification) | UpDn · VQA-CP v2 test | overall accuracy: 39.49 -> 48.87 | Improved |
| add decomposed linguistic representations | SAN · VQA-CP v2 test | overall accuracy: 24.96 -> 34.83 | Improved |
| add decomposed linguistic representations | UpDn · VQA v2 val | overall accuracy: 62.85 -> 57.96 | Hurt |
| add language attention module (vs GRU) (ablation) | Ours · VQA-CP v2 test | overall accuracy: 41.49 -> 48.87 | Improved |
| add threshold and category loss to modular attention (ablation) | Ours · VQA-CP v2 test | overall accuracy: 42.50 -> 48.87 | Improved |
| add Q&A mask generation (ablation) | Ours · VQA-CP v2 test other | accuracy: 36.59 -> 45.57 | Improved |
| increase language attention threshold (ablation) | Ours · VQA-CP v2 vs VQA v2 | accuracy | Mixed |
Closest papers by meaning
- Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (CVPR 2018 · similarity 0.92)
- Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (CVPR 2017 · similarity 0.92)
- HybridPrompt: Bridging Language Models and Human Priors in Prompt Tuning for Visual Question Answering (AAAI 2023 · similarity 0.92)
- Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool (TPAMI 2018 · similarity 0.91)
- Exploring Question Decomposition for Zero-Shot VQA (NeurIPS 2023 · 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.
