GVdoc: Graph-based Visual Document Classification
This addresses robustness issues in visual document classification for real-world deployment, offering a more efficient and effective solution.
The paper tackled the problem of visual document classifiers struggling with out-of-distribution data and high computational costs, proposing GVdoc, a graph-based model that outperforms state-of-the-art models on out-of-distribution data with fewer parameters while maintaining comparable in-distribution performance.
The robustness of a model for real-world deployment is decided by how well it performs on unseen data and distinguishes between in-domain and out-of-domain samples. Visual document classifiers have shown impressive performance on in-distribution test sets. However, they tend to have a hard time correctly classifying and differentiating out-of-distribution examples. Image-based classifiers lack the text component, whereas multi-modality transformer-based models face the token serialization problem in visual documents due to their diverse layouts. They also require a lot of computing power during inference, making them impractical for many real-world applications. We propose, GVdoc, a graph-based document classification model that addresses both of these challenges. Our approach generates a document graph based on its layout, and then trains a graph neural network to learn node and graph embeddings. Through experiments, we show that our model, even with fewer parameters, outperforms state-of-the-art models on out-of-distribution data while retaining comparable performance on the in-distribution test set.