Official PyTorch implementation of ''Exploring Intrinsic Discrimination and Consistency for Weakly Supervised Object Localization'' (IDC).
Our code is released under the Creative Commons BY-NC-SA 3.0 (see LICENSE for more details), available only for non-commercial use.
git clone https://github.com/vignywang/IDC.git
cd IDC-master
datasets
└───CUB_200_2011
└───train
└───test
model name | GT-known Loc % |
---|---|
vgg_CUB |
93.36 |
resnet_CUB |
95.59 |
python train.py --gpu 0
python evaluation.py --config ${congfigs/vgg_CUB.yaml} --gpu 0 --epoch 29
The evaluation results will be displayed as:
Cls-Loc acc 0.7236417930523903
Cls-Loc acc Top 5 0.8606499876562411
GT Loc acc 0.9335930243796378
MaxBoxAccV2 acc 0.8715766827518584
Part of our evaluation and training code based on PSOL (CVPR2020), BAS (CVPR2022) and CREAM (CVPR2022).
Thanks for their works and sharing.