Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain-Robust VQA With Diverse Datasets and Methods but No Target Labels
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use two-stage DANN instead of direct transfer | MAC · VQA v2 to stylized VQA v2 | accuracy: 41.0 -> 42.8 | Helped |
| Use two-stage DANN instead of one-stage DANN (ablation) | MAC · VQA v2 to stylized VQA v2 | accuracy: 42.2 -> 42.8 | Helped |
| Use two-stage DANN instead of moment matching (ablation) | MAC · VQA v2 to stylized VQA v2 | accuracy: 42.6 -> 42.8 | Helped |
| Use two-stage DANN instead of direct transfer | MAC · CLEVR to stylized CLEVR | accuracy: 45.9 -> 46.7 | Helped |
| Use two-stage DANN instead of one-stage DANN (ablation) | MAC · MAC on stylized CLEVR | accuracy: 45.7 -> 46.7 | Helped |
| Use two-stage DANN instead of moment matching (ablation) | MAC · CLEVR to stylized CLEVR | accuracy: 46.6 -> 46.7 | No clear effect |
| Use two-stage DANN instead of direct transfer | MAC · GQA Balanced to stylized GQA Balanced | accuracy: 37.3 -> 38.5 | Helped |
| Use two-stage DANN instead of one-stage DANN (ablation) | MAC · GQA Balanced to stylized GQA Balanced | accuracy: 37.4 -> 38.5 | Helped |
| Use two-stage DANN instead of moment matching (ablation) | MAC · GQA Balanced to stylized GQA Balanced | accuracy: 38.6 -> 38.5 | Hurt |
| Apply two-stage DANN to the source-trained model | NSCL · CLEVR stylized images | accuracy: 59.7 -> 68.6 | Helped |
| Apply two-stage DANN to the source-trained model | MAC · CLEVR stylized images | accuracy: 62.6 -> 65.2 | Helped |
| Apply two-stage DANN to the source-trained model | TbD · CLEVR stylized images | accuracy: 36.3 -> 41.3 | Helped |
Closest papers by meaning
- Cross-Dataset Adaptation for Visual Question Answering (CVPR 2018 · similarity 0.91)
- Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning (CVPR 2023 · similarity 0.91)
- FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering (CVPR 2025 · similarity 0.89)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.89)
- Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy (ICLR 2024 · similarity 0.87)
- VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models (AAAI 2024 · similarity 0.87)
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.