search

y0ast / deterministic-uncertainty-quantification

Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"
https://arxiv.org/abs/2003.02037
MIT License
268 stars 31 forks source link

Feasibility for object detection #7

Closed hantaotao closed 2 years ago

hantaotao commented 2 years ago

Hello，Can this method be used for object detection? Have you done relevant experiments? Thank you so much!

y0ast commented 2 years ago

Hmm, DUQ cannot be easily extended to regression, so bounding box object detection would be difficult.

We do have a follow up (workshop) paper on semantic segmentation: https://arxiv.org/abs/2111.00079 based on a different but similar method.

leyuan-sun commented 2 years ago

Hmm, DUQ cannot be easily extended to regression, so bounding box object detection would be difficult.

We do have a follow up (workshop) paper on semantic segmentation: https://arxiv.org/abs/2111.00079 based on a different but similar method.

One object detction network is developed bases on your DUQ, https://ieeexplore.ieee.org/abstract/document/9627771, published on RA-L recently.

I will also try to implment your method on 6D pose regression task.

y0ast commented 2 years ago

Thank you for sharing this :)