Learning Rich Image Region Representation for Visual Question Answering
This work addresses performance in VQA, a key task in AI for image understanding, but it is incremental as it builds on existing methods with ensemble techniques.
The paper tackled improving Visual Question Answering (VQA) by enhancing visual and text feature representations, using detection techniques for visual features and BERT for text features, resulting in a second-place finish in the VQA Challenge 2019.
We propose to boost VQA by leveraging more powerful feature extractors by improving the representation ability of both visual and text features and the ensemble of models. For visual feature, some detection techniques are used to improve the detector. For text feature, we adopt BERT as the language model and find that it can significantly improve VQA performance. Our solution won the second place in the VQA Challenge 2019.