Simple Baseline for Visual Question Answering
2015-12-07Code Available0· sign in to hype
Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/metalbubble/VQAbaselineOfficialIn papernone★ 0
- github.com/karunraju/VQApytorch★ 0
- github.com/sidaw/nbsvmnone★ 0
- github.com/yikang-li/iqanpytorch★ 0
- github.com/sidgan/whats_in_a_questionnone★ 0
- github.com/SkyOL5/VQA-CoAttentionpytorch★ 0
- github.com/miohana/vqatf★ 0
Abstract
We describe a very simple bag-of-words baseline for visual question answering. This baseline concatenates the word features from the question and CNN features from the image to predict the answer. When evaluated on the challenging VQA dataset [2], it shows comparable performance to many recent approaches using recurrent neural networks. To explore the strength and weakness of the trained model, we also provide an interactive web demo and open-source code. .
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| COCO Visual Question Answering (VQA) real images 1.0 multiple choice | iBOWIMG baseline | Percentage correct | 62 | — | Unverified |
| COCO Visual Question Answering (VQA) real images 1.0 open ended | iBOWIMG baseline | Percentage correct | 55.9 | — | Unverified |