VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks
This addresses the problem of limited domain generalization research in vision-language tasks for researchers, but it is incremental as it focuses on dataset creation rather than novel methods.
The authors tackled the lack of datasets for domain generalization in vision-language tasks by introducing VolDoGer, a dataset for image captioning, visual question answering, and visual entailment, and evaluated models on it, showing performance variations across domains.
Domain generalizability is a crucial aspect of a deep learning model since it determines the capability of the model to perform well on data from unseen domains. However, research on the domain generalizability of deep learning models for vision-language tasks remains limited, primarily because of the lack of required datasets. To address these challenges, we propose VolDoGer: Vision-Language Dataset for Domain Generalization, a dedicated dataset designed for domain generalization that addresses three vision-language tasks: image captioning, visual question answering, and visual entailment. We constructed VolDoGer by extending LLM-based data annotation techniques to vision-language tasks, thereby alleviating the burden of recruiting human annotators. We evaluated the domain generalizability of various models, ranging from fine-tuned models to a recent multimodal large language model, through VolDoGer.