Skip to content

Code for our ICCV 2021 paper "Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting"

License

Notifications You must be signed in to change notification settings

rayleizhu/FDRNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FDRNet

Code for our ICCV 2021 paper "Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting"

pipeline

How to Use

create conda environment

conda env create -f env.yaml

To use CRF refinement, you will need to mannually install pydensecrf.

WARNING: To reproduce the results reported in our paper, please make sure major pacakges (pytorch, opencv, etc.) are with the same version speficified in env.yaml.

run inference

  • download the checkpoint from here.
  • specify data_root, and run python test.py.
  • run python crf_refine.py.
  • check the results w/ and w/o CRF refinement in test/raw and test/crf respectively

Results

BER scores are specified below.

SBU UCF ISTD
w/o CRF 3.27 7.42 1.53
w/ CRF 3.04 7.28 1.55

You can access qualitative reseults from BaiduNetDisk (passcode:4j3i).

TODOs

  • move the logic of brightness shift to the dataset class; rewrite dataset class.
  • remove feature extraction hook, use segmentation_models.pytorch encoder instead.
  • use timm's register_model decorator

About

Code for our ICCV 2021 paper "Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting"

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages