Data augmentation; False positive; Tiny object detection; Augmentation techniques; Negative samples; Objects detection; Target object; Training image; Training process
Abstract :
[en] Detecting tiny objects is a fundamental task in computer vision but poses a considerable challenge for existing detectors. One issue is that task-irrelevant objects or non-object background patches can be mistakenly detected as objects of interest, significantly impairing detector precision. To tackle this issue we propose an online image augmentation technique, NegCopyPaste, in the training process. This method copies regions of training images falsely identified as target objects in one epoch and pastes them into the training images for the next epoch. By training the model to reject false-positive predictions made in previous epochs, the proposed method effectively decreases the proportion of false-positive predictions compared to the baselines, making the network more selective in picking out the target objects. NegCopyPaste reduces the number of false-positive predictions during inference and achieves new state-of-the-art results on TinyPerson, WiderFace and DOTA, notably improving mAPtiny by 1.58% over the previous best method on TinyPerson.
Disciplines :
Computer science
Author, co-author :
Ning, Jinlai ; King’s College London, London, United Kingdom
SPRATLING, Michael ; University of Luxembourg > Faculty of Humanities, Education and Social Sciences (FHSE) > Department of Behavioural and Cognitive Sciences (DBCS) > Cognitive Science and Assessment ; King’s College London, London, United Kingdom
Gionfrida, Letizia ; King’s College London, London, United Kingdom
External co-authors :
yes
Language :
English
Title :
Improving the Accuracy of Tiny Object Detection by Negative Sample Copy-Paste
Publication date :
2025
Event name :
International Conference on Neural Information Processing (ICONIP)
Event place :
Auckland, Nzl
Event date :
02-12-2024 => 06-12-2024
Audience :
International
Main work title :
Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings
Editor :
Mahmud, Mufti
Publisher :
Springer Science and Business Media Deutschland GmbH, Germany
The authors gratefully acknowledge the support of the King\u2019s Computational Research, Engineering and Technology Environment (CREATE) and Joint Academic Data Science Endeavour (JADE). This research was funded by the King\u2019s-China Scholarship Council (K-CSC).
Bell, S., Zitnick, C.L., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Bosquet, B., Cores, D., Seidenari, L., Brea, V.M., Mucientes, M., Bimbo, A.D.: A full data augmentation pipeline for small object detection based on generative adversarial networks. Pattern Recogn. 133, 108998 (2023). https://doi.org/10.1016/j.patcog.2022.108998
Deng, J., Fan, D., Qiu, X., Zhou, F.: Improving crowded object detection via copy-paste. In: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence. AAAI Press (2023). https://doi.org/10.1609/aaai.v37i1.25124
Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2918–2928 (2021)
Hong, M., Li, S., Yang, Y., Zhu, F., Zhao, Q., Lu, L.: SSPNet: scale selection pyramid network for tiny person detection from UAV images. IEEE Geosci. Remote Sensing Lett. (2021)
Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Jiang, N., Yu, X., Peng, X., Gong, Y., Han, Z.: SM+: refined scale match for tiny person detection. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021). https://doi.org/10. 1109/icassp39728.2021.9414162
Kisantal, M., Wojna, Z., Murawski, J., Naruniec, J., Cho, K.: Augmentation for small object detection. In: 9th International Conference on Advances in Computing and Information Technology (ACITY 2019) (2019). https://doi.org/10.5121/csit. 2019.91713
Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)
Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Liu, G., Han, J., Rong, W.: Feedback-driven loss function for small object detection. Image Vis. Comput. 104197 (2021). https://doi.org/10.1016/j.imavis.2021. 104197
Niebles, J.C., Krishna, R.: Lecture 15: detecting objects by parts. In: Computer Vision: Foundations and Applications—Stanford Course CS131. Stanford University (2017). http://vision.stanford.edu/teaching/cs131 fall1718/files/15 notes.pdf
Ning, J., Guan, H., Spratling, M.: Rethinking the backbone architecture for tiny object detection. In: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023)-Volume 5: VISAPP, pp. 103–114. INSTICC, SciTePress (2023). https://doi.org/10.5220/0011643500003417
Ning, J., Spratling, M.: The importance of anti-aliasing in tiny object detection. arXiv e-prints arXiv:2310.14221 (Oct 2023)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024– 8035. Curran Associates, Inc. (2019)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788 (2016). https://doi.org/10.1109/CVPR.2016.91
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc. (2015)
Saito, K., Hu, P., Darrell, T., Saenko, K.: Learning to detect every thing in an open world. In: Computer Vision – ECCV 2022, pp. 268–284. Springer Nature Switzerland, Cham (2022)
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 761–769 (2016). https://doi.org/10.1109/CVPR.2016.89
Singh, B., Davis, L.S.: An analysis of scale invariance in object detection: SNIP. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Singh, B., Najibi, M., Davis, L.: SNIPER: efficient multi-scale training. In: Neural Information Processing Systems (2017)
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Van Rossum, G., Drake, F.L.: Python 3 Reference Manual. CreateSpace, Scotts Valley, CA (2009)
Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.S.: Tiny object detection in aerial images. In: ICPR, pp. 3791–3798 (2021)
Xia, G.S., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented R-CNN for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 3520–3529 (2021)
Xu, C., Wang, J., Yang, W., Yu, H., Yu, L., Xia, G.S.: RFLA: gaussian receptive field based label assignment for tiny object detection. In: European Conference on Computer Vision, pp. 526–543. Springer (2022)
Xu, C., Wang, J., Yang, W., Yu, L.: Dot distance for tiny object detection in aerial images. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1192–1201 (2021). https://doi.org/10.1109/CVPRW53098.2021.00130
Yang, S., Luo, P., Loy, C.C., Tang, X.: WIDER FACE: a face detection benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z.: Scale match for tiny person detection. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) (2020). https://doi.org/10.1109/wacv45572.2020.9093394
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021)
Zhu, Y., Cai, H., Zhang, S., Wang, C., Xiong, Y.: Tinaface: strong but simple baseline for face detection. arXiv preprint arXiv:2011.13183 (2020)
