Efficient Object Detection via Sparse Representation and Structural Reconstruction
Article Sidebar
Main Article Content
Abstract
This paper proposes an efficient object detection method based on sparse representation and structural reconstruction to address the problems of feature redundancy, missing structural information, and limited computational efficiency in object detection. The method introduces a sparse constraint mechanism during feature extraction to effectively select key features and suppress irrelevant information, achieving compression and optimization in the feature space. At the structural level, a graph-based reconstruction module is designed to model topological relationships and semantic propagation among nodes, restoring spatial dependencies and structural consistency of the targets. The overall architecture integrates sparse feature constraints, structural reconstruction, and global optimization, achieving significant improvement in inference efficiency while maintaining high detection accuracy. Using the MS COCO dataset as the validation platform, experimental results show that the proposed method outperforms mainstream detection models in Precision, Recall, mAP@50, and mAP@50-95 metrics. Particularly under complex scenes and multi-scale conditions, the model demonstrates stronger stability and generalization, maintaining high-quality detection with low computational cost. By integrating sparse feature representation with structural modeling, this study provides a solution that balances performance and interpretability for efficient object detection.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Mind forge Academia also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.
References
Roh B, Shin J W, Shin W, et al. Sparse detr: Efficient end-to-end object detection with learnable sparsity[J]. arXiv preprint arXiv:2111.14330, 2021.
H. Zhang, H. Zhang, A. Mei, Z. Gan and G. N. Zhu, "SO-DETR: Leveraging dual-domain features and knowledge distillation for small object detection," Proceedings of the 2025 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2025.
Liao Y, Chen G, Xu R. Enhanced sparse detection for end-to-end object detection[J]. IEEE Access, 2022, 10: 85630-85640.
Liu K, Fu Z, Jin S, et al. ESOD: efficient small object detection on high-resolution images[J]. IEEE Transactions on Image Processing, 2024.
Li S, Huang J. Resgdanet: An efficient residual group attention neural network for medical image classification[J]. Applied Sciences, 2025, 15(5): 2693.
J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You only look once: Unified, real-time object detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.
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.
T. Y. Lin, P. Goyal, R. Girshick, K. He and P. Dollár, "Focal loss for dense object detection," Proceedings of the IEEE International Conference on Computer Vision, pp. 2980-2988, 2017.
N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov and S. Zagoruyko, "End-to-end object detection with transformers," European Conference on Computer Vision, pp. 213-229, 2020.
Y. Zhao et al., "DETRs beat YOLOs on real-time object detection," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965-16974, 2024.
X. Wang, R. Girshick, A. Gupta and K. He, "Non-local neural networks," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794-7803, 2018.
N. Hoanh and T. V. Pham, "End-to-end transformer-based detection with density-guided query selection for small objects," Neurocomputing, 2025..
C. Yang, Z. Huang and N. Wang, "QueryDet: Cascaded sparse query for accelerating high-resolution small object detection," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13668-13677, 2022.
P. Sun et al., "RSN: Range sparse net for efficient, accurate LiDAR 3D object detection," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5725-5734, 2021.
S. Yuan et al., "SP-KAN: Sparse-sine perception Kolmogorov-Arnold networks for infrared small target detection," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 234, pp. 1-19, 2026.
T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," arXiv preprint arXiv:1609.02907, 2016.
C. Hu et al., "Structural generalization for microservice routing using graph neural networks," Proceedings of the International Conference on Artificial Intelligence and Automation Control, pp. 278-282, 2025.
X. Song et al., "Multi-scale feature fusion and graph neural network integration for text classification with large language models," arXiv preprint arXiv:2511.05752, 2025.
A. Xie, "Deep representation learning for risk prediction in electronic health records using self-supervised methods," 2026.
L. Yan, Q. Wang and J. Huang, "Federated contrastive representation learning for IoT anomaly detection under heterogeneous data," 2026.
X. Yang, Y. Wang, Y. Li and S. Sun, "Semantics-aware denoising: A PLM-guided sample reweighting strategy for robust recommendation," arXiv preprint arXiv:2602.15359, 2026.
C. Shao et al., "Adversarial robustness in text classification through semantic calibration with large language models," 2026.
J. Zheng et al., "Structured prompt optimization for few-shot text classification via semantic alignment in latent space," arXiv preprint arXiv:2602.23753, 2026.
Z. Zhang et al., "CondenseGraph: Communication-efficient distributed GNN training via on-the-fly graph condensation," arXiv preprint arXiv:2601.17774, 2026.
C. Chiang, "Collaborative machine learning for risk ranking under concurrent class imbalance and distribution shift," 2026.
T. D. Nguyen, S. Marchal, M. Miettinen, H. Fereidooni, N. Asokan and A. R. Sadeghi, "DÏoT: A federated self-learning anomaly detection system for IoT," Proceedings of the 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), pp. 756-767, 2019.
C. Nie, "Adaptive ETL task scheduling via hierarchical reinforcement learning with joint rewards for latency and load balancing," 2026.
L. Yang et al., "Cognitive modeling for long-horizon agent learning via integrated long-term memory and reasoning," 2026.
J. Chen et al., "SecureGov-Agent: A governance-centric multi-agent framework for privacy-preserving and attack-resilient LLM agents," 2025.
Y. Hu et al., "TrustOrch: A dynamic trust-aware orchestration framework for adversarially robust multi-agent collaboration," 2025.
R. Liu, L. Yang, R. Zhang and S. Wang, "Generative modeling of human-computer interfaces with diffusion processes and conditional control," arXiv preprint arXiv:2601.06823, 2026.
P. Pan and D. Wu, "Trustworthy summarization via uncertainty quantification and risk awareness in large language models," Proceedings of the International Conference on Computer Vision and Data Mining, pp. 523-527, 2025.
A. Kirillov et al., "Segment anything," Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4015-4026, 2023.
C. Chen et al., "SE-RSRNet: Rain streak removal by feature selection and feature extraction," Applied Soft Computing, 2026.