GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
This addresses the challenge of few-shot learning for vision-language models, enabling better performance on diverse tasks like visual question answering and grounding, though it appears incremental as it builds on existing few-shot methods.
The paper tackles the problem of few-shot generalization in vision-language tasks, such as object grounding and multi-image reasoning, by introducing GRILL, a model that learns object-text alignments to enable zero-/few-shot transfer, achieving state-of-the-art performance on various tasks.
Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks. However, such generalization to vision-language tasks including grounding and generation tasks has been under-explored; existing few-shot VL models struggle to handle tasks that involve object grounding and multiple images such as visual commonsense reasoning or NLVR2. In this paper, we introduce GRILL, GRounded vIsion Language aLigning, a novel VL model that can be generalized to diverse tasks including visual question answering, captioning, and grounding tasks with no or very few training instances. Specifically, GRILL learns object grounding and localization by exploiting object-text alignments, which enables it to transfer to grounding tasks in a zero-/few-shot fashion. We evaluate our model on various zero-/few-shot VL tasks and show that it consistently surpasses the state-of-the-art few-shot methods.