The PyTorch code for "Integral Object Mining via Online Attention Accumulation", which is implemented based on the code of psa and ACoL.
python3
torch >= 1.0
tqdm
torchvision
python-opencv
Download the VOCdevkit.tar.gz file and extract it into data/ folder.
cd OAA-PyTorch/
./train.sh
After the training process, you can resize the accumulated attention map to original image size.
cd ./runs/exp1/
python res.py
For a comparison with the attention maps generated by the final classification model, you can generate them by
./test.sh
Pre-accumulated maps and models [link]
If you want to skip the online attention accumulation process to train the integral model directly, Download the pre-accumulated maps and
extract them to exp1/
.
./train_iam.sh
./test_iam.sh
If you have any question about OAA, please feel free to contact Me (pt.jiang AT mail DOT nankai.edu.cn).