Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 2 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.1%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: fehmikahraman
- License: apache-2.0
- Language: Python
- Default Branch: main
- Size: 6.02 MB
Statistics
- Stars: 23
- Watchers: 2
- Forks: 3
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Correlation Loss: Enforcing Correlation between Classification and Localization
The official implementation of Correlation Loss. Our implementation is based on mmdetection.
Correlation Loss: Enforcing Correlation between Classification and Localization,
Fehmi Kahraman, Kemal Oksuz, Sinan Kalkan, Emre Akbas, AAAI 2023.
How to Cite
Please cite the paper if you benefit from our paper or the repository:
Kahraman, F., Oksuz, K., Kalkan, S., & Akbas, E. (2023).
Correlation Loss: Enforcing Correlation between Classification and Localization.
Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 1087-1095.
https://doi.org/10.1609/aaai.v37i1.25190
Specification of Dependencies and Preparation
- Please see get_started.md for requirements and installation of MMDetection.
- Please refer to introduction.md for dataset preparation and basic usage of MMDetection.
Training Code
The configuration files of all models listed above can be found in the configs/CorrLoss folder. You can follow introduction.md for training code. As an example, to train Sparse R-CNN with our Correlation Loss on 4 GPUs as we did, use the following command:
./tools/dist_train.sh configs/CorrLoss/sparse_rcnn_r50_fpn_1x_coco_spearman_02.py 4
Test Code
The configuration files of all models listed above can be found in the configs/CorrLoss folder. You can follow introduction.md for test code. As an example, first download a trained model using the links provided in the tables or you train a model, then run the following command to test an object detection model on multiple GPUs:
./tools/dist_test.sh configs/CorrLoss/sparse_rcnn_r50_fpn_1x_coco_spearman_02.py ${CHECKPOINT_FILE} 4 --eval bbox
and use the following command to test an instance segmentation model on multiple GPUs:
./tools/dist_test.sh configs/CorrLoss/yolact_r50_4x8_coco_spearman_02.py ${CHECKPOINT_FILE} 4 --eval bbox segm
You can also test a model on a single GPU with the following example command:
python tools/test.py configs/CorrLoss/sparse_rcnn_r50_fpn_1x_coco_spearman_02.py ${CHECKPOINT_FILE} --eval bbox
Details for Correlation Loss Implementation
Below is the links to the most relevant files that can be useful check out the details of the implementation: - CorrATSSHead and implementation of the Correlation Loss - CorrFoveaHead - CorrPAAHead - DIIHead for Corr Sparse-RCNN - Config files folder of Correlation Loss
Owner
- Name: fehmi kahraman
- Login: fehmikahraman
- Kind: user
- Repositories: 2
- Profile: https://github.com/fehmikahraman
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "MMDetection Contributors" title: "OpenMMLab Detection Toolbox and Benchmark" date-released: 2018-08-22 url: "https://github.com/open-mmlab/mmdetection" license: Apache-2.0
GitHub Events
Total
Last Year
Dependencies
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- cython *
- numpy *
- docutils ==0.16.0
- recommonmark *
- sphinx ==4.0.2
- sphinx-copybutton *
- sphinx_markdown_tables *
- sphinx_rtd_theme ==0.5.2
- mmcv-full >=1.3.17
- cityscapesscripts *
- imagecorruptions *
- scipy *
- sklearn *
- mmcv *
- torch *
- torchvision *
- matplotlib *
- numpy *
- pycocotools *
- pycocotools-windows *
- six *
- terminaltables *
- asynctest * test
- codecov * test
- flake8 * test
- interrogate * test
- isort ==4.3.21 test
- kwarray * test
- mmtrack * test
- onnx ==1.7.0 test
- onnxruntime >=1.8.0 test
- pytest * test
- ubelt * test
- xdoctest >=0.10.0 test
- yapf * test