Research map / Vision-language and multimodal / Visual question answering
Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an adaptive multi-margin collaborative debiasing approach to mitigate language bias in visual question answering and improve out-of-distribution robustness.
Problem
Language bias in VQA, where models exploit spurious correlations between question templates and answers, neglecting visual cues especially under out-of-distribution shift.
Approach
Adaptive multi-margin collaborative debiasing to make VQA models resilient to language bias; based only on the abstract, the specific mechanism is not fully described.
Closest papers by meaning
- FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in 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)
- CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark (NeurIPS 2024 · similarity 0.90)
- Towards Robust Visual Question Answering via Prompt-Driven Geometric Harmonization (AAAI 2025 · similarity 0.90)
- NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples (NeurIPS 2024 · similarity 0.90)
- Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering (NeurIPS 2024 · similarity 0.89)
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.