Author(s)

Qiang Zeng^*, YiDan Chen

Affiliation(s)

School of Computer Science and Artificial Intelligence, Beijing Technology and Business University, Beijing 102488, China.

Corresponding Author

Qiang Zeng

ABSTRACT

In object detection tasks, the sparse distribution, weak saliency and context-dependent nature of small objects pose three major challenges for perception systems. Although end-to-end detection architectures like the YOLO series have achieved a good balance between and speed accuracy in recent years, their utilization of shallow-layer features is low, resulting in performance bottlenecks in micro-object recognition. To address this, this paper proposes a small-object perception-enhanced detection framework, TFE-Net (Tiny-aware Feature Enhancement Network). By constructing a shallow high-resolution feature pathway and a multi-scale fine-grained semantic interaction module, it achieves a lightweight improvement of the YOLOv8s model structure. While maintaining the original model's computational complexity, this method significantly enhances the spatial perception and discrimination accuracy for extremely small objects. Experiments were conducted on the VisDrone dataset. Results show that the improved model boosts the mAP@0.5 from 0.386 to 0.421, with noticeable improvements in PR curves across all categories. This confirms the proposed strategy's ability to perceptually reconstruct and detect small objects in complex scenarios.

KEYWORDS

Small object detection; Feature enhancement network; YOLOv8; Multi-scale fusion; Weak saliency awareness

CITE THIS PAPER

Qiang Zeng, YiDan Chen. TFE-NET: a tiny-aware feature enhancement network for collaborative optimization in small object detection. Journal of Computer Science and Electrical Engineering. 2025, 7(4): 66-73. DOI: https://doi.org/10.61784/jcsee3071.

REFERENCES

[1] Tian H, Zheng Y, Jin Z. Improved RetinaNet model for the application of small target detection in the aerial images//IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2020, 585(1): 012142.

[2] Ahmed M, Wang Y, Maher A, et al. Fused RetinaNet for small target detection in aerial images. International Journal of Remote Sensing, 2022, 43(8): 2813-2836.

[3] Ahmad M, Abdullah M, Han D. Small object detection in aerial imagery using RetinaNet with anchor optimization//2020 International conference on electronics, information, and communication (ICEIC). IEEE, 2020: 1-3.

[4] Dubey S, Olimov F, Rafique M A, et al. Improving small objects detection using transformer. Journal of Visual Communication and Image Representation, 2022, 89: 103620.

[5] Dai X, Chen Y, Yang J, et al. Dynamic detr: End-to-end object detection with dynamic attention//Proceedings of the IEEE/CVF international conference on computer vision. IEEE, 2021, 10: 2988-2997.

[6] Cao X, Yuan P, Feng B, et al. Cf-detr: Coarse-to-fine transformers for end-to-end object detection//Proceedings of the AAAI conference on artificial intelligence. AAAI, 2022, 36(1): 185-193.

[7] Wang H, Liu C, Cai Y, et al. YOLOv8-QSD: An improved small object detection algorithm for autonomous vehicles based on YOLOv8. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 1-1.

[8] Sun S, Mo B, Xu J, et al. Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle. Neurocomputing, 2024, 588: 127685.

[9] Shen L, Lang B, Song Z. DS-YOLOv8-based object detection method for remote sensing images. IEEE Access, 2023, 11: 125122-125137.

[10] Du D, Zhu P, Wen L, et al. VisDrone-DET2019: The vision meets drone object detection in image challenge results//Proceedings of the IEEE/CVF international conference on computer vision workshops. IEEE, 2019, 1: 0-0.