search

TRAILab / CaDDN

Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 Oral)
Apache License 2.0
359 stars 62 forks source link

How much performance degrade with lighter backbone ? #35

Closed henniekim closed 3 years ago

henniekim commented 3 years ago

Hello !

The backbone used in this paper is heavy which leads to the slower inference time. Have you ever tried lighter backbone such as Mobile Deeplab ?

I'd like to figure out how much performance degrade when using lighter backbone network.

Thanks a lot :)

codyreading commented 3 years ago

Hi and thanks for the interest!

I haven't tried using the Mobile Deeplab (as it wasn't released on torchvision at the time of development), but it definitely is possible. I would guess somewhere between 2-5% AP.