Dynamic Anchor: A Feature-Guided Anchor Strategy for Object Detection
Source abstract
Abstract
The majority of modern object detectors rely on a set of pre-defined anchor boxes, which enhances detection performance dramatically. Nevertheless, the pre-defined anchor strategy suffers some drawbacks, especially the complex hyper-parameters of anchors, seriously affecting detection performance. In this paper, we propose a feature-guided anchor generation method named dynamic anchor. Dynamic anchor mainly includes two structures: the anchor generator and the feature enhancement module. The anchor generator leverages semantic features to predict optimized anchor shapes at the locations where the objects are likely to exist in the feature maps; by converting the predicted shape maps into location offsets, the feature enhancement module uses the high-quality anchors to improve detection performance. Compared with the hand-designed anchor scheme, dynamic anchor discards all pre-defined boxes and avoids complex hyper-parameters. In addition, only one anchor box is predicted for each location, which dramatically reduces calculation. With ResNet-50 and ResNet-101 as the backbone of the one-stage detector RetinaNet, dynamic anchor achieved 2.1 AP and 1.0 AP gains, respectively. The proposed dynamic anchor strategy can be easily integrated into the anchor-based detectors to replace the traditional pre-defined anchor scheme.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China
Funding
Sichuan Major Science and Technology Special Project
References (35)
Show source-provided references
1. Zou, Z., Shi, Z., Guo, Y., and Ye, J. (2019). Object detection in 20 years: A survey. arXiv.
2. Multi-level cross-modal interaction network for RGB-D salient object detection10.1016/j.neucom.2021.04.053 ↗
3. Liu, B., Chen, H., Huang, Z., Liu, X., and Yang, Y. (2021). ZoomInNet: A Novel Small Object Detector in Drone Images with Cross-Scale Knowledge Distillation. Remote Sens., 13.10.3390/rs13061198 ↗
4. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
5. 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 ↗
6. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
7. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., and Berg, A. (2016, January 11–14). Ssd: Single Shot Multibox Detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
8. 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 ↗
9. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (1, January June). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
10. Huang, L., Yang, Y., Deng, Y., and Yu, Y. (2015). Densebox: Unifying landmark localization with end to end object detection. arXiv.
11. Yu, J., Jiang, Y., Wang, Z., Cao, Z., and Huang, T. (2016, January 15–19). Unitbox: An Advanced Object Detection Network. Proceedings of the 24th ACM International Conference on Multimedia, Amsterdam, The Netherlands.10.1145/2964284.2967274 ↗
12. Law, H., and Deng, J. (2018, January 8–14). Cornernet: Detecting Objects as Paired Keypoints. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01264-9_45 ↗
13. Zhu, C., He, Y., and Savvides, M. (2019, January 15–20). Feature Selective Anchor-Free Module for Single-Shot Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00093 ↗
14. Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (2019, January 27–28). Centernet: Keypoint Triplets for Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea.10.1109/ICCV.2019.00667 ↗
15. Foveabox: Beyound Anchor-Based Object Detection10.1109/TIP.2020.3002345 ↗
16. Deep learning for generic object detection: A survey10.1007/s11263-019-01247-4 ↗
17. Zhang, S., Chi, C., Yao, Y., Lei, Z., and Li, S.Z. (2020, January 16–18). Bridging the Gap between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00978 ↗
18. Tian, Z., Shen, C., Chen, H., and He, T. (November, January 27). Fcos: Fully Convolutional One-Stage Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea.
19. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
20. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014, January 6–12). Microsoft Coco: Common Objects in Context. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
21. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
22. Wang, J., Chen, K., Yang, S., Loy, C.C., and Lin, D. (2019, January 15–20). Region Proposal by Guided Anchoring. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00308 ↗
23. Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., and Ling, H. (February, January January). M2det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
24. Zhang, S., Wen, L., Bian, X., Lei, Z., and Li, S.Z. (2018, January 18–22). 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 ↗
25. Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., and Berg, A.C. (2017). Dssd: Deconvolutional single shot detector. arXiv.
26. Dai, J., Li, Y., He, K., and Sun, J. (2016). R-fcn: Object Detection via Region-Based Fully Convolutional Networks. Advances in Neural Information Processing Systems, Proceedings of the 2016 Conference on Neural Information Processing Systems, Barcelona, Spain, 5–10 December 2016, NIPS.
27. Cai, Z., and Vasconcelos, N. (2018, January 18–22). 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 ↗
28. Cascade region proposal and global context for deep object detection10.1016/j.neucom.2017.12.070 ↗
29. Kim, K., and Lee, H.S. (2020, January 23–28). Probabilistic Anchor Assignment with Iou Prediction for Object Detection. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58595-2_22 ↗
30. Yang, T., Zhang, X., Li, Z., Zhang, W., and Sun, J. (2018, January 2–8). Metaanchor: Learning to Detect Objects with Customized Anchors. Advances in Neural Information Processing Systems, Montreal, QC, Canada.
31. Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y. (2017, January 22–29). Deformable Convolutional Networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.89 ↗
32. Neubeck, A., and Van Gool, L. (2006, January 20–24). Efficient Non-Maximum Suppression. Proceedings of the 18th International Conference on Pattern Recognition, Hong Kong, China.10.1109/ICPR.2006.479 ↗
33. Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., and Lin, D. (2019). MMDetection: Open mmlab detection toolbox and benchmark. arXiv.
34. Imagenet classification with deep convolutional neural networks
35. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01234-2_1 ↗