Research map / Architectures and efficiency / CNN design
Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction
Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han
Check 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 |
|---|---|---|---|
| use dynamic parameter prediction instead of concatenating image and question features (ablation) | DPPnet · VQA test-dev | accuracy: 54.70 -> 55.46 | Improved |
| pre-train GRU on a large text corpus (ablation) | DPPnet · VQA test-dev | accuracy: 55.46 -> 56.74 | Improved |
| fine-tune CNN weights (ablation) | DPPnet · VQA test-dev | accuracy: 56.74 -> 57.22 | Improved |
| use dynamic parameter prediction instead of concatenating image and question features (ablation) | DPPnet · VQA test-dev | multiple-choice accuracy: 59.92 -> 61.18 | Improved |
| add GRU pre-training (ablation) | DPPnet · VQA test-dev | multiple-choice accuracy: 61.18 -> 61.95 | Improved |
| fine-tune CNN weights (ablation) | DPPnet · VQA test-dev | multiple-choice accuracy: 61.95 -> 62.48 | Improved |
| fine-tune the CNN directly from the start rather than delaying updates to transferred layers | DPPnet · ImageQA | accuracy | No clear effect |
| use an un-pretrained GRU rather than a pre-trained GRU (ablation) | DPPnet · VQA test-dev | accuracy: 56.74 -> 55.46 | Hurt |
Closest papers by meaning
- Learning to Answer Questions from Image Using Convolutional Neural Network (AAAI 2016 · similarity 0.92)
- Image Captioning and Visual Question Answering Based on Attributes and External Knowledge (TPAMI 2017 · similarity 0.90)
- Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge (CVPR 2018 · similarity 0.89)
- Visual Question Answering with Question Representation Update (QRU) (NeurIPS 2016 · similarity 0.88)
- An Analysis of Visual Question Answering Algorithms (ICCV 2017 · similarity 0.88)
- Multi-Level Attention Networks for Visual Question Answering (CVPR 2017 · 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.
