Repository files navigation

by Chi, Cheng and Wei, Fangyun and Hu, Han

Existing object detection frameworks are usually built on a single format of objject/part representation, i.e., anchor/proposal rectangle boxes in RetinaNet andFaster R-CNN, center points in FCOS and RepPoints, and corner points in CornerNet. While these different representations usually drive the frameworks to performwell in different aspects, e.g., better classification or finer localization, it is in general difficult to combine these representations in a single framework to make gooduse of each strength, due to the heterogeneous or non-grid feature extraction by different representations. This paper presents an attention-based decoder modulesimilar as that in Transformer to bridge other representations into a typical object detector built on a single representation format, in an end-to-end fashion. The other representations act as a set of key instances to strengthen the main query representation features in the vanilla detectors. Novel techniques are proposed towards efficient computation of the decoder module, including a key sampling approach and a shared location embedding approach. The proposed module is named bridging visual representations (BVR).

• Install it

bash install.sh${your_code_dir}cd${your_code_dir}mkdir -p data ln -s${your_coco_path} data/coco

whereyour_code_dir is your code path andyour_coco_path is the location of extracted coco dataset on your server. For more information, you may refer togetting started

• For testing

bash tools/dist_test.sh${selected_config} 8

whereselected_config is one of provided script under theconfig/bvr folder.

• For training

bash tools/dist_train.sh${selected_config} 8

whereselected_config is one of provided script under theconfig/bvr folder.

• For more dataset

We have not trained or tested on other dataset. If you would like to use it on other data, please refer tommdetection.

@inproceedings{relationnetplusplus2020,  title={RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder},  author={Chi, Cheng and Wei, Fangyun and Hu, Han},  booktitle={NeurIPS},  year={2020}}

This project welcomes contributions and suggestions. Most contributions require you to agree to aContributor License Agreement (CLA) declaring that you have the right to, and actually do, grant usthe rights to use your contribution. For details, visithttps://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to providea CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructionsprovided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted theMicrosoft Open Source Code of Conduct.For more information see theCode of Conduct FAQ orcontactopencode@microsoft.com with any additional questions or comments.

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsofttrademarks or logos is subject to and must followMicrosoft's Trademark & Brand Guidelines.Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.Any use of third-party trademarks or logos are subject to those third-party's policies.