Research map / Vision-language and multimodal / Visual question answering
Learning to Disambiguate by Asking Discriminative Questions
Yining Li, Chen Huang, Xiaoou Tang, Chen Change Loy
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 question similarity term to attribute contrast (ablation) | ACQG · VDQG (full) | BLEU: 52.9 -> 59.1 | Improved |
| add visual dissimilarity term (ablation) | ACQG · VDQG (full) | BLEU: 59.1 -> 59.4 | Improved |
| add visual dissimilarity term (ablation) | ACQG · VDQG (full) | Delta BLEU: 40.1 -> 40.6 | Improved |
| add question similarity term to attribute contrast (ablation) | ACQG · VDQG (hard subset) | BLEU: 44.3 -> 53.2 | Improved |
| add visual dissimilarity term (ablation) | ACQG · VDQG (hard subset) | BLEU: 53.2 -> 53.6 | Improved |
| add visual dissimilarity term (ablation) | ACQG · VDQG (hard subset) | Delta BLEU: 32.6 -> 33.5 | Improved |
| add question similarity term to attribute contrast (ablation) | ACQG · VDQG (full) | Delta BLEU: 29.4 -> 40.1 | Improved |
| add question similarity term to attribute contrast (ablation) | ACQG · VDQG (hard subset) | Delta BLEU: 13.5 -> 32.6 | Improved |
| attribute score contrast alone instead of CNN-LSTM (no attributes guidance via similarity) (ablation) | ACQG · VDQG (full) | BLEU: 56.2 -> 52.9 | Hurt |
| full attribute-guided model vs CNN-LSTM baseline | ACQG · VDQG (full) | BLEU: 56.2 -> 59.4 | Improved |
| full attribute-guided model vs CNN-LSTM baseline | ACQG · VDQG (hard subset) | BLEU: 47.8 -> 53.6 | Improved |
| full attribute-guided model vs CNN-LSTM baseline | ACQG · VDQG (hard subset) | Delta BLEU: 20.3 -> 33.5 | Improved |
Closest papers by meaning
- An Analysis of Visual Question Answering Algorithms (ICCV 2017 · similarity 0.91)
- Learning Answer Embeddings for Visual Question Answering (CVPR 2018 · similarity 0.91)
- Image Captioning and Visual Question Answering Based on Attributes and External Knowledge (TPAMI 2017 · similarity 0.91)
- Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (CVPR 2017 · similarity 0.91)
- An Empirical Evaluation of Visual Question Answering for Novel Objects (CVPR 2017 · similarity 0.90)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · 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.
