This is the official repository for "Efficient Classification of Very Large Images with Tiny Objects".
An increasing number of applications in computer vision, specially, in medical imaging and remote sensing, become challenging when the goal is to classify very large images with tiny informative objects.
Specifically, these classification tasks face two key challenges:
pytorch-gpu == 1.6.0
torchvision == 0.7.0
training on colon cancer dataset:
python main.py /path_to_your_dataset/ /path_to_your_output/ --mode 10CrossValidation --model_name yourModelName
python main.py /path_to_your_dataset/ /path_to_your_model_directory/ --mode Evaluation --model_name yourModelName
This work was supported by NIH (R44-HL140794), DARPA (FA8650-18-2-7832-P00009-12) and ONR (N00014-18-1-2871-P00002-3).
If you would like to cite our work,
@inproceedings{kong2022efficient,
title={Efficient Classification of Very Large Images with Tiny Objects},
author={Kong, Fanjie and Henao, Ricardo},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={2384--2394},
year={2022}
}