search

imatge-upc / rvos

RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)
https://imatge-upc.github.io/rvos/
Other
277 stars 54 forks source link

zero shot model results: 10 instances highly redundant #13

Open miibotree opened 5 years ago

miibotree commented 5 years ago

when I use zero-shot pre-trained model to run my own videos, the model output 10 instances which is highly redundant(usually highly overlapped at one object)，how can we choose the best object result?

carlesventura commented 5 years ago

In that case, the reason could be that the model is not able to find any other relevant instance in the image and I would choose the first mask given by the decoder.

Best regards,

Carles