Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5 (2402.14309v2)

Published 22 Feb 2024 in cs.CV

Abstract: Object detection, a crucial aspect of computer vision, has seen significant advancements in accuracy and robustness. Despite these advancements, practical applications still face notable challenges, primarily the inaccurate detection or missed detection of small objects. In this paper, we propose YOLO-TLA, an advanced object detection model building on YOLOv5. We first introduce an additional detection layer for small objects in the neck network pyramid architecture, thereby producing a feature map of a larger scale to discern finer features of small objects. Further, we integrate the C3CrossCovn module into the backbone network. This module uses sliding window feature extraction, which effectively minimizes both computational demand and the number of parameters, rendering the model more compact. Additionally, we have incorporated a global attention mechanism into the backbone network. This mechanism combines the channel information with global information to create a weighted feature map. This feature map is tailored to highlight the attributes of the object of interest, while effectively ignoring irrelevant details. In comparison to the baseline YOLOv5s model, our newly developed YOLO-TLA model has shown considerable improvements on the MS COCO validation dataset, with increases of 4.6% in [email protected] and 4% in [email protected]:0.95, all while keeping the model size compact at 9.49M parameters. Further extending these improvements to the YOLOv5m model, the enhanced version exhibited a 1.7% and 1.9% increase in [email protected] and [email protected]:0.95, respectively, with a total of 27.53M parameters. These results validate the YOLO-TLA model's efficient and effective performance in small object detection, achieving high accuracy with fewer parameters and computational demands.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, “Object detection in 20 years: A survey,” Proceedings of the IEEE, 2023.
  2. R. Kaur and S. Singh, “A comprehensive review of object detection with deep learning,” Digital Signal Processing, vol. 132, p. 103812, 2023.
  3. S. Xu, M. Zhang, W. Song, H. Mei, Q. He, and A. Liotta, “A systematic review and analysis of deep learning-based underwater object detection,” Neurocomputing, 2023.
  4. Q. Zhao, B. Liu, S. Lyu, C. Wang, and H. Zhang, “Tph-yolov5++: Boosting object detection on drone-captured scenarios with cross-layer asymmetric transformer,” Remote Sensing, vol. 15, no. 6, p. 1687, 2023.
  5. J. Mao, S. Shi, X. Wang, and H. Li, “3d object detection for autonomous driving: A comprehensive survey,” International Journal of Computer Vision, pp. 1–55, 2023.
  6. L. Zhang, G. Wang, M. Chen, F. Ren, and L. Shao, “An enhanced noise-tolerant hashing for drone object detection,” Pattern Recognition, vol. 143, p. 109762, 2023.
  7. H.-K. Jung and G.-S. Choi, “Improved yolov5: Efficient object detection using drone images under various conditions,” Applied Sciences, vol. 12, no. 14, p. 7255, 2022.
  8. M. Woźniak, M. Wieczorek, and J. Siłka, “Deep neural network with transfer learning in remote object detection from drone,” in Proceedings of the 5th international ACM mobicom workshop on drone assisted wireless communications for 5G and beyond, 2022, pp. 121–126.
  9. A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.
  10. Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, “Yolox: Exceeding yolo series in 2021,” arXiv preprint arXiv:2107.08430, 2021.
  11. C. Li, L. Li, H. Jiang, K. Weng, Y. Geng, L. Li, Z. Ke, Q. Li, M. Cheng, W. Nie et al., “Yolov6: A single-stage object detection framework for industrial applications,” arXiv preprint arXiv:2209.02976, 2022.
  12. Y. Ghasemi, H. Jeong, S. H. Choi, K.-B. Park, and J. Y. Lee, “Deep learning-based object detection in augmented reality: A systematic review,” Computers in Industry, vol. 139, p. 103661, 2022.
  13. Y. Liu, Z. Shao, and N. Hoffmann, “Global attention mechanism: Retain information to enhance channel-spatial interactions,” arXiv preprint arXiv:2112.05561, 2021.
  14. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.
  15. R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440–1448.
  16. S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, vol. 28, 2015.
  17. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
  18. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14.   Springer, 2016, pp. 21–37.
  19. J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
  20. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 936–944.
  21. K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian, “Centernet: Keypoint triplets for object detection,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 6569–6578.
  22. M. Tan, R. Pang, and Q. V. Le, “Efficientdet: Scalable and efficient object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 10 781–10 790.
  23. S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path aggregation network for instance segmentation,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 8759–8768.
  24. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
  25. N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-end object detection with transformers,” in European conference on computer vision.   Springer, 2020, pp. 213–229.
  26. C. Wang, W. He, Y. Nie, J. Guo, C. Liu, K. Han, and Y. Wang, “Gold-yolo: Efficient object detector via gather-and-distribute mechanism,” arXiv preprint arXiv:2309.11331, 2023.
  27. S. Chen, P. Sun, Y. Song, and P. Luo, “Diffusiondet: Diffusion model for object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 19 830–19 843.
  28. D. Zheng, W. Dong, H. Hu, X. Chen, and Y. Wang, “Less is more: Focus attention for efficient detr,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 6674–6683.
  29. Y. Li, Y. Chen, N. Wang, and Z. Zhang, “Scale-aware trident networks for object detection,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 6054–6063.
  30. J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
  31. S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “Cbam: Convolutional block attention module,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 3–19.
  32. X. Li, W. Wang, X. Hu, and J. Yang, “Selective kernel networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 510–519.
  33. Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, “Eca-net: Efficient channel attention for deep convolutional neural networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 534–11 542.
  34. Q. Hou, D. Zhou, and J. Feng, “Coordinate attention for efficient mobile network design,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 13 713–13 722.
  35. Q.-L. Zhang and Y.-B. Yang, “Sa-net: Shuffle attention for deep convolutional neural networks,” in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).   IEEE, 2021, pp. 2235–2239.
  36. X. Zhang, C. Liu, D. Yang, T. Song, Y. Ye, K. Li, and Y. Song, “Rfaconv: Innovating spatital attention and standard convolutional operation,” arXiv preprint arXiv:2304.03198, 2023.
  37. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” in European Conference on Computer Vision (ECCV).   Springer-Verlag, 2014, pp. 740–755.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Peng Gao (401 papers)
  2. Chun-Lin Ji (1 paper)
  3. Tao Yu (282 papers)
  4. Ru-Yue Yuan (7 papers)
  5. Fei Wang (573 papers)
Citations (10)
View on Semantic Scholar