VirTex: Learning Visual Representations from Textual Annotations
This addresses the data efficiency problem for computer vision researchers and practitioners by offering a more resource-effective alternative to traditional pretraining methods.
The paper tackles the problem of learning high-quality visual representations from fewer images by proposing VirTex, a pretraining approach using semantically dense captions, which matches or exceeds ImageNet-supervised or unsupervised features on tasks like image classification, object detection, and instance segmentation while using up to ten times fewer images.
The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored unsupervised pretraining to scale to vast quantities of unlabeled images. In contrast, we aim to learn high-quality visual representations from fewer images. To this end, we revisit supervised pretraining, and seek data-efficient alternatives to classification-based pretraining. We propose VirTex -- a pretraining approach using semantically dense captions to learn visual representations. We train convolutional networks from scratch on COCO Captions, and transfer them to downstream recognition tasks including image classification, object detection, and instance segmentation. On all tasks, VirTex yields features that match or exceed those learned on ImageNet -- supervised or unsupervised -- despite using up to ten times fewer images.