3 papers
cs.CV2025
A biologically inspired separable learning vision model for real-time traffic object perception in Dark
Hulin Li, Qiliang Ren, Jun Li +3
Fast and accurate object perception in low-light traffic scenes has attracted increasing attention. However, due to severe illumination degradation and the lack of reliable visual…
cs.CV2025
Rethinking Features-Fused-Pyramid-Neck for Object Detection
Hulin Li
Multi-head detectors typically employ a features-fused-pyramid-neck for multi-scale detection and are widely adopted in the industry. However, this approach faces feature misalignm…
cs.CV2024
Slim-neck by GSConv: A lightweight-design for real-time detector architectures
Hulin Li, Jun Li, Hanbing Wei +3
Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement and a light…