Towards General Purpose Vision Systems
arXiv:2104.00743
Abstract
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.
CVPR 2022 Oral; Project page: https://prior.allenai.org/projects/gpv
References in corpus (6)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Learning Transferable Visual Models From Natural Language Supervision
- Language Models are Few-Shot Learners
- Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
- One Model To Learn Them All
- Unifying Vision-and-Language Tasks via Text Generation