KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
This work addresses the problem of generating commonsense descriptions from visual and textual inputs for AI systems, offering an incremental improvement to existing methods.
This paper introduces KM-BART, a Transformer-based sequence-to-sequence model that integrates commonsense knowledge from multimodal inputs (images and text) for Visual Commonsense Generation (VCG). By adapting the BART architecture and developing novel pretraining tasks, including Knowledge-based Commonsense Generation (KCG), the model achieves state-of-the-art performance on the VCG task.
We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the generative BART architecture to a multimodal model with visual and textual inputs. We further develop novel pretraining tasks to improve the model performance on the Visual Commonsense Generation (VCG) task. In particular, our pretraining task of Knowledge-based Commonsense Generation (KCG) boosts model performance on the VCG task by leveraging commonsense knowledge from a large language model pretrained on external commonsense knowledge graphs. To the best of our knowledge, we are the first to propose a dedicated task for improving model performance on the VCG task. Experimental results show that our model reaches state-of-the-art performance on the VCG task by applying these novel pretraining tasks.