Research map / Vision-language and multimodal / Visual question answering
Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder
Gouthaman KV, Anurag Mittal
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 |
|---|---|---|---|
| replace the GRU question encoder with VGQE | Baseline (RUBi base model) · VQA-CPv2 test | overall accuracy: 38.46 -> 50.11 | Improved |
| replace the GRU question encoder with VGQE | UpDn · VQA-CPv2 test | overall accuracy: 39.74 -> 48.75 | Improved |
| replace the GRU question encoder with VGQE | BAN · VQA-CPv2 test | overall accuracy: 39.31 -> 50.0 | Improved |
| replace the GRU question encoder with VGQE | UpDn · VQAv2 val | overall accuracy: 63.48 -> 64.04 | Improved |
| replace the GRU question encoder with VGQE | Baseline (RUBi base model) · VQAv2 val | overall accuracy: 63.10 -> 63.18 | No clear effect |
| replace the GRU question encoder with VGQE | BAN · VQAv2 val | overall accuracy: 65.36 -> 65.73 | Improved |
| add RUBi question-only branch | Baseline · VQAv2 val | overall accuracy: 63.10 -> 61.16 | Hurt |
| add RUBi question-only branch | Baseline · VQA-CPv2 test | overall accuracy: 38.46 -> 47.11 | Improved |
| add LangAtt debiasing | UpDn · VQAv2 val | overall accuracy: 63.48 -> 57.96 | Hurt |
| add SCR with extra human attention annotations | UpDn · VQAv2 val | overall accuracy: 63.48 -> 62.2 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MUREL — MUREL: Multimodal Relational Reasoning for Visual Question Answering (CVPR 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RMLVQA: A Margin Loss Approach for Visual Question Answering With Language Biases (CVPR 2023 · similarity 0.93)
- Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (CVPR 2018 · similarity 0.93)
- Robust Visual Question Answering: Datasets, Methods, and Future Challenges (TPAMI 2024 · similarity 0.93)
- Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models (ICLR 2024 · similarity 0.92)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.91)
- Can I Trust Your Answer? Visually Grounded Video Question Answering (CVPR 2024 · similarity 0.91)
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.
