Towards Flexible Multi-modal Document Models
This work addresses the need for holistic models in creative workflows for designers, though it appears incremental as it builds on existing multi-modal and pre-training techniques.
The authors tackled the problem of jointly solving multiple design tasks for graphical documents by developing FlexDM, a unified model that predicts masked fields like element type and styling attributes, achieving competitive performance with task-specific baselines.
Creative workflows for generating graphical documents involve complex inter-related tasks, such as aligning elements, choosing appropriate fonts, or employing aesthetically harmonious colors. In this work, we attempt at building a holistic model that can jointly solve many different design tasks. Our model, which we denote by FlexDM, treats vector graphic documents as a set of multi-modal elements, and learns to predict masked fields such as element type, position, styling attributes, image, or text, using a unified architecture. Through the use of explicit multi-task learning and in-domain pre-training, our model can better capture the multi-modal relationships among the different document fields. Experimental results corroborate that our single FlexDM is able to successfully solve a multitude of different design tasks, while achieving performance that is competitive with task-specific and costly baselines.