A Novel Small Target Detection Strategy: Location Feature Extraction in the Case of Self-Knowledge Distillation
Source abstract
Abstract
Small target detection has always been a hot and difficult point in the field of target detection. The existing detection network has a good effect on conventional targets but a poor effect on small target detection. The main challenge is that small targets have few pixels and are widely distributed in the image, so it is difficult to extract effective features, especially in the deeper neural network. A novel plug-in to extract location features of the small target in the deep network was proposed. Because the deep network has a larger receptive field and richer global information, it is easier to establish global spatial context mapping. The plug-in named location feature extraction establishes the spatial context mapping in the deep network to obtain the global information of scattered small targets in the deep feature map. Additionally, the attention mechanism can be used to strengthen attention to the spatial information. The comprehensive effect of the above two can be utilized to realize location feature extraction in the deep network. In order to improve the generalization of the network, a new self-distillation algorithm was designed for pre-training that could work under self-supervision. The experiment was conducted on the public datasets (Pascal VOC and Printed Circuit Board Defect dataset) and the self-made dedicated small target detection dataset, respectively. According to the diagnosis of the false-positive error distribution, the location error was significantly reduced, which proved the effectiveness of the plug-in proposed for location feature extraction. The mAP results can prove that the detection effect of the network applying the location feature extraction strategy is much better than the original network.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Industrial Vision Systems and Defect Detection · Infrared Target Detection Methodologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
School of Electronics and Information Engineering, Tiangong University, Tianjin 300387, China
School of Software, Tiangong University, Tianjin 300387, China
Funding
China Postdoctoral Science Foundation
References (63)
Show source-provided references
1. 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 ↗
2. 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 ↗
3. Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., and Ouyang, W. (2019, January 15–20). Hybrid task cascade for instance segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00511 ↗
4. 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 contex. Proceedings of the Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
5. Chen, C., Liu, M.Y., Tuzel, O., and Xiao, J. (2016, January 20–24). R-CNN for small object detection. Proceedings of the Computer Vision–ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan.10.1007/978-3-319-54193-8_14 ↗
6. A Survey and Performance Evaluation of Deep Learning Methods for Small Object Detection10.1016/j.eswa.2021.114602 ↗
7. Methods for Small, Weak Object Detection in Optical High-Resolution Remote Sensing Images: A survey of advances and challenges10.1109/MGRS.2020.3041450 ↗
8. Recent Advances in Small Object Detection
9. A Survey of the Four Pillars for Small Object Detection: Multiscale Representation, Contextual Information, Super-Resolution, and Region Proposal10.1109/TSMC.2020.3005231 ↗
10. 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 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
11. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). SSD: Single shot multibox detector. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
12. Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., and Berg, A.C. (2017). DSSD: Deconvolutional Single Shot Detector. arXiv.
13. Kong, T., Yao, A., Chen, Y., and Sun, F. (2016, January 27–30). HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.98 ↗
14. 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 ↗
15. Lim, J.S., Astrid, M., Yoon, H.J., and Lee, S.I. (2021, January 13–16). Small Object Detection using Context and Attention. Proceedings of the 2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Jeju Island, Republic of Korea.10.1109/ICAIIC51459.2021.9415217 ↗
16. Aguinaldo, A., Chiang, P.Y., Gain, A., Patil, A., Pearson, K., and Feizi, S. (2019). Pearson and S. Feizi. Compressing GANs using Knowledge Distillation. arXiv.
17. Ahn, S., Hu, S.X., Damianou, A., Lawrence, N.D., and Dai, Z. (2019, January 15–20). Variational Information Distillation for Knowledge Transfer. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00938 ↗
18. Aditya, S., Saha, R., Yang, Y., and Baral, C. (2019, January 7–11). Spatial Knowledge Distillation to Aid Visual Reasoning. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, HI, USA.10.1109/WACV.2019.00030 ↗
19. Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey10.1109/TPAMI.2020.2992393 ↗
20. Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H. (2020, January 14–19). CSPNet: A New Backbone that can Enhance Learning Capability of CNN. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
21. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
22. Cui, L., Ma, R., Lv, P., Jiang, X., Gao, Z., Zhou, B., and Xu, M. (2018). MDSSD: Multi-scale deconvolutional single shot detector for small objects. arXiv.
23. Small traffific sign detection from large image10.1007/s10489-019-01511-7 ↗
24. Detecting small objects using a channel-aware deconvolutional network10.1109/TCSVT.2019.2906246 ↗
25. Bell, S., Zitnick, C.L., Bala, K., and Girshick, R. (2016, January 27–30). Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.314 ↗
26. Robust obstacle detection and recognition for driver assistance systems10.1109/TITS.2019.2909275 ↗
27. Chen, X.L., and Gupta, A. (2017, January 22–29). Spatial Memory for Context Reasoning in Object Detection. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.440 ↗
28. Hu, H., Gu, J., Zhang, Z., Dai, J., and Wei, Y. (2018, January 18–22). Relation Networks for Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00378 ↗
29. Jie, H., Li, S., and Gang, S. (2018, January 18–22). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.
30. Mo, K. (2017). Spatial Transformer Network. Neural Inf. Process. Syst., 2017–2025.
31. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018). CBAM: Convolutional Block Attention Module. ECCV, 3–19.10.1007/978-3-030-01234-2_1 ↗
32. Hou, Q., Zhou, D., and Feng, J. (2021, January 19–25). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.10.1109/CVPR46437.2021.01350 ↗
33. Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv.
34. Self-Distillation: Towards Efficient and Compact Neural Networks
35. Zhang, L., Song, J., Gao, A., Chen, J., Bao, C., and Ma, K. (November, January 27). Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00381 ↗
36. Yang, C., Xie, L., Su, C., and Yuille, A.L. (2019, January 15–20). Snapshot Distillation: Teacher-Student Optimization in One Generation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00297 ↗
37. Phuong, M., and Lampert, C. (November, January 27). Distillation-Based Training for Multi-Exit Architectures. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00144 ↗
38. Self-Distillation Amplifies Regularization in Hilbert Space
39. Self-Distillation as Instance-Specific Label Smoothing
40. Oord, A.V.D., Li, Y., and Vinyals, O. (2018). Representation Learning with Contrastive Predictive Coding. arXiv.
41. He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 14–19). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00975 ↗
42. Chen, X., Fan, H., Girshick, R., and He, K. (2020). Improved Baselines with Momentum Contrastive Learning. arXiv.
43. Chopra, S., Hadsell, R., and LeCun, Y. (2005, January 20–26). Learning a similarity metric discriminatively, with application to face verification. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA.
44. Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13–18). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the International Conference on Machine Learning, Virtual.
45. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., and Joulin, A. (2020, January 6–12). Unsupervised Learning of Visual Features by Contrasting Cluster Assignments. Proceedings of the 34th Conference on Neural Information Processing Systems, Online.
46. Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
47. Chen, X., and He, K. (2021). Exploring Simple Siamese Representation Learning. Comput. Vis. Pattern Recognit., 15745–15753.10.1109/CVPR46437.2021.01549 ↗
48. Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the International Conference on Machine Learning, Lille, France.
49. Group Normalization10.1007/s11263-019-01198-w ↗
50. Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer Normalization. arXiv.
51. Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2016). Instance Normalization: The Missing Ingredient for Fast Stylization. arXiv.
52. Ortiz, A., Robinson, C., Morris, D., Fuentes, O., Kiekintveld, C., Hassan, M.M., and Jojic, N. (2020, January 14–19). Local Context Normalization: Revisiting Local Normalization. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01129 ↗
53. Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep Sparse Rectifier Neural Networks. Proceedings of the fourteenth international conference on artificial intelligence and statistics, Ft. Lauderdale, FL, USA.
54. Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00140 ↗
55. Self-Knowledge Distillation with Progressive Refinement of Targets
56. Improving Transferability of Representations via Augmentation-Aware Self-Supervision
57. Bochkovskiy, A., Wang, C.Y., and Liao, H. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
58. A fast accurate fine-grain object detection model based on YOLOv4 deep neural network10.1007/s00521-021-06651-x ↗
59. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–23). Path Aggregation Network for Instance Segmentation. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
60. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition10.1109/TPAMI.2015.2389824 ↗
61. The Pascal Visual Object Classes Challenge: A Retrospective10.1007/s11263-014-0733-5 ↗
62. Hoiem, D., Chodpathumwan, Y., and Dai, Q. (2012, January 7–13). Diagnosing Error in Object Detectors. Proceedings of the 12th European Conference on Computer Vision, Florence, Italy. Part III.10.1007/978-3-642-33712-3_25 ↗
63. Wang, C.Y., Bochkovskiy, A., and Liao, H. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.