BBRefinement: A Universal Scheme to Improve the Precision of Box Object Detectors
Source abstract
Abstract
We present a conceptually simple yet powerful and general scheme for refining the predictions of bounding boxes produced by an arbitrary object detector. Our approach was trained separately on single objects extracted from ground truth labels. For inference, it can be coupled with an arbitrary object detector to improve its precision. The method, called BBRefinement, uses a mixture of data consisting of the image crop of an object and the object’s class and center. Because BBRefinement works in a restricted domain, it does not have to be concerned with multiscale detection, recognition of the object’s class, computing confidence, or multiple detections. Thus, the training is much more effective. It results in the ability to improve the performance of SOTA architectures by up to two mAP points on the COCO dataset in the benchmark. The refinement process is fast; it adds 50–80 ms overhead to a standard detector using RTX2080; therefore, it can run in real time on standard hardware. Finally, we show that BBRefinement can also be applied to COCO’s ground truth labels to create new, more precise labels. The link to the source code is provided in the contribution.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Centre of Excellence IT4Innovations, Institute for Research and Applications of Fuzzy Modeling, 30. Dubna 22, University of Ostrava, 702 00 Ostrava, Czech Republic
Varroc Lighting Systems, Suvorovova 195, 742 42 Šenov u Nového Jičína, Czech Republic
References (28)
Show source-provided references
1. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014). Microsoft coco: Common objects in context. European Conference on Computer Vision, Springer.10.1007/978-3-319-10602-1_48 ↗
2. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
3. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7–12). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
4. Gidaris, S., and Komodakis, N. (2015, January 7–13). Object detection via a multi-region and semantic segmentation-aware cnn model. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.135 ↗
5. Multistage object detection with group recursive learning10.1109/TMM.2017.2772796 ↗
6. Gong, J., Zhao, Z., and Li, N. (2019, January 9–12). Improving Multi-stage Object Detection via Iterative Proposal Refinement. Proceedings of the BMVC, Cardiff, UK.
7. Zhang, S., Wen, L., Bian, X., Lei, Z., and Li, S.Z. (2018, January 18–23). Single-shot refinement neural network for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00442 ↗
8. RefineDet++: Single-Shot Refinement Neural Network for Object Detection10.1109/TCSVT.2020.2986402 ↗
9. Cai, Z., and Vasconcelos, N. (2018, January 18–23). Cascade r-cnn: Delving into high quality object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00644 ↗
10. Object detection with discriminatively trained part-based models10.1109/TPAMI.2009.167 ↗
11. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016). Ssd: Single shot multibox detector. European Conference on Computer Vision, Springer.10.1007/978-3-319-46448-0_2 ↗
12. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
13. Law, H., and Deng, J. (2018, January 8–14). Cornernet: Detecting objects as paired keypoints. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01264-9_45 ↗
14. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020). End-to-End Object Detection with Transformers. arXiv.10.1007/978-3-030-58452-8_13 ↗
15. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
16. Tan, M., and Le, Q.V. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv.
17. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
18. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15–20). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00075 ↗
19. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (, January 7–12). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), New York, New York, USA, 2020.
20. Zeiler, M.D. (2012). Adadelta: An adaptive learning rate method. arXiv.
21. Smith, L.N. (2017, January 24–31). Cyclical learning rates for training neural networks. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.10.1109/WACV.2017.58 ↗
22. Pizer, S.M., Johnston, R.E., Ericksen, J.P., Yankaskas, B.C., and Muller, K.E. Contrast-limited adaptive histogram equalization: Speed and effectiveness. Proceedings of the First Conference on Visualization in Biomedical Computing.
23. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
24. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
25. Brock, A., De, S., and Smith, S.L. (2021). Characterizing signal propagation to close the performance gap in unnormalized ResNets. arXiv.
26. Impact of training set batch size on the performance of convolutional neural networks for diverse datasets
27. Qiao, S., Chen, L.C., and Yuille, A. (2020). DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution. arXiv.10.1109/CVPR46437.2021.01008 ↗
28. Hurtik, P., Molek, V., Hula, J., Vajgl, M., Vlasanek, P., and Nejezchleba, T. (2020). Poly-YOLO: Higher speed, more precise detection and instance segmentation for YOLOv3. arXiv.