Work

ContextFlow-YOLO: Context Preservation and Cross-Scale Redistribution for Small-Object Detection in Complex Environments

Year: 2026

Type: article

Abstract: Small objects in underwater and traffic-sign images often have weak boundaries and low contrast. Downsampling and multi-scale fusion can further weaken the features needed to detect them. We propose ContextFlow-YOLO, a YOLOv8n-based detector designed to preserve context during feature extraction and reuse it across scales. Its context-preserving backbone combines local features with surrounding and global information during downsampling. The global-guided scale-sequence neck distributes this context to features at different levels. A nonlinear context-attention fusion unit then refines the responses used for prediction. ContextFlow-YOLO obtains [email protected] scores of 0.855, 0.838, and 0.826 on URPC2019, URPC2020, and TT100K, respectively. On TT100K, the model uses 6.11 M parameters and runs at 134 FPS. Heatmap and receptive-field visualizations show more concentrated target responses and broader feature coverage than YOLOv8n.

Source: Mathematics

DOI: 10.3390/math14203781

Authors: Yuqing Jiao, Siok Yee Tan, Fadilla ’Atyka Nor Rashid, Huifen Xing, Yong Zhang

Institutions: Chaohu University, National University of Malaysia

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,137

Funders: Ministry of Higher Education, Malaysia, Universiti Kebangsaan Malaysia, Anhui Provincial Department of Education