Open-vocabulary Object Detection via Vision and Language Knowledge Distillation. (arXiv:2104.13921v3 [cs.CV] UPDATED)

We aim at advancing open-vocabulary object detection, which detects objects
described by arbitrary text inputs. The fundamental challenge is the
availability of training data. It is costly to further scale up the number of
classes contained in existing object detection datasets. To overcome this
challenge, we propose ViLD, a training method via Vision and Language knowledge
Distillation. Our method distills the knowledge from a pretrained
open-vocabulary image classification model (teacher) into a two-stage detector
(student). Specifically, we use the teacher …

arxiv cv detection distillation knowledge language vision