Improved RAMEN: Towards Domain Generalization for Visual Question Answering
This work addresses the lack of model generalization in VQA, which is a bottleneck for real-world applications, but it is incremental as it builds upon an existing architecture.
The paper tackled the problem of domain generalization in Visual Question Answering (VQA) by improving the RAMEN model with new fusion and aggregation modules, resulting in performance gains on up to five VQA datasets.
Currently nearing human-level performance, Visual Question Answering (VQA) is an emerging area in artificial intelligence. Established as a multi-disciplinary field in machine learning, both computer vision and natural language processing communities are working together to achieve state-of-the-art (SOTA) performance. However, there is a gap between the SOTA results and real world applications. This is due to the lack of model generalisation. The RAMEN model \cite{Shrestha2019} aimed to achieve domain generalization by obtaining the highest score across two main types of VQA datasets. This study provides two major improvements to the early/late fusion module and aggregation module of the RAMEN architecture, with the objective of further strengthening domain generalization. Vector operations based fusion strategies are introduced for the fusion module and the transformer architecture is introduced for the aggregation module. Improvements of up to five VQA datasets from the experiments conducted are evident. Following the results, this study analyses the effects of both the improvements on the domain generalization problem. The code is available on GitHub though the following link \url{https://github.com/bhanukaManesha/ramen}.