论文标题
有效的Floodnet VQA的现代基线
An Efficient Modern Baseline for FloodNet VQA
论文作者
论文摘要
在灾难管理和响应系统的情况下，设计高效且可靠的VQA系统仍然是一个具有挑战性的问题。在这项工作中，我们重新审视基本组合方法，例如串联，加法和元素乘法与现代图像和文本特征抽象模型。我们设计了一个简单有效的系统，该系统的表现优于洪水数据集上的预先存在的方法并实现最先进的性能。与现代VQA架构相比，这种简化的系统所需的培训时间和推理时间要少得多。我们还研究了各种骨干的性能，并报告其合并结果。代码可在https://github.com/sahilkhose/floodnet_vqa上找到。
Designing efficient and reliable VQA systems remains a challenging problem, more so in the case of disaster management and response systems. In this work, we revisit fundamental combination methods like concatenation, addition and element-wise multiplication with modern image and text feature abstraction models. We design a simple and efficient system which outperforms pre-existing methods on the FloodNet dataset and achieves state-of-the-art performance. This simplified system requires significantly less training and inference time than modern VQA architectures. We also study the performance of various backbones and report their consolidated results. Code is available at https://github.com/sahilkhose/floodnet_vqa.
