Towards General Purpose Vision Systems
This work addresses the problem of reducing development time and expertise for creating new vision applications, though it appears incremental as it builds on existing vision-language models.
The paper tackles the challenge of adapting computer vision systems to new tasks by proposing GPV-1, a task-agnostic vision-language architecture that can perform tasks like classification and visual question answering without modifications, achieving zero-shot performance on the Referring Expressions task and improvements with few training samples.
Computer vision systems today are primarily N-purpose systems, designed and trained for a predefined set of tasks. Adapting such systems to new tasks is challenging and often requires non-trivial modifications to the network architecture (e.g. adding new output heads) or training process (e.g. adding new losses). To reduce the time and expertise required to develop new applications, we would like to create general purpose vision systems that can learn and perform a range of tasks without any modification to the architecture or learning process. In this paper, we propose GPV-1, a task-agnostic vision-language architecture that can learn and perform tasks that involve receiving an image and producing text and/or bounding boxes, including classification, localization, visual question answering, captioning, and more. We also propose evaluations of generality of architecture, skill-concept transfer, and learning efficiency that may inform future work on general purpose vision. Our experiments indicate GPV-1 is effective at multiple tasks, reuses some concept knowledge across tasks, can perform the Referring Expressions task zero-shot, and further improves upon the zero-shot performance using a few training samples.