According to the GLIP paper,† accuracy on a test-set not seen during training is around 60% so... neat demos but whether it'll be reliable enough depends on your application.
† https://arxiv.org/abs/2206.05836
According to the GLIP paper,† accuracy on a test-set not seen during training is around 60% so... neat demos but whether it'll be reliable enough depends on your application.
† https://arxiv.org/abs/2206.05836