Sep 2026· ELCVIA Electronic Letters on Computer Vision and Image Analysis· 0 citations· 28 references
TL;DR
Tests on the COCO dataset show that EnYOLO-World offers a better trade-off between accuracy and speed compared to existing real-time detectors, demonstrating the value of optimizing both backbone feature retention and neck-level fusion strategies.
Abstract
Real-time object detection needs to strike a balance between accuracy, speed, and reliability. However,many YOLO-based models struggle with two main issues: weakened feature quality in deeper backbonelayers and inefficient multiscale fusion in the detection neck. To overcome these challenges, we presentEnYOLO-World — a refined detection framework that combines the YOLOv9 GELAN backbone withProgrammable Gradient Information (PGI) to retain detailed spatial features and ensure smoother gradi-ent flow. We also introduce a FiLM-Driven Path Aggregation Network (FiLM-PAN), which adaptivelyfuses multiscale features using channel-wise affine transformations, achieving efficient performance withlinear complexity. Tests on the COCO dataset show that EnYOLO-World offers a better trade-off betweenaccuracy and speed compared to existing real-time detectors, demonstrating the value of optimizing bothbackbone feature retention and neck-level fusion strategies.
This work proposesours, an aerial-image detector built on the YOLO12 architecture, which combines a triple-path high-frequency enhancement convolution module (TriPathHFConv), receptive-field coordinate-attention convolution (RFCAConv), and a Mamba-based global-context module.
This work introduces a Tri-Directional Attention module into the backbone of the YOLOv11 baseline framework, modeling the spatial position information via a three-way attention mechanism to capture richer fine-grained features and devise a Cross-Dimension Feature Interaction module to enhance the recognition accuracy f...
C. Dong, Jianwei Hu· Journal of Real-Time Image P...· 0 citations
Renowned for its real-time detection capabilities, RT-DETR efficiently performs object detection in complex scenarios. However, small-object detection, particularly in remote sensing or maritime imagery, is frequently hindered by background interference, occlusion, and diminutive object features, thus limiting overall...
Chen-Bo Shi, Yin-Kai Zhu, Chun Zhang et al.· IEEE Geoscience and Remote S...· 0 citations
A two-stage hand analysis framework that combines an optimized YOLOv5s detector with HRNet-based keypoint estimation and an adapted MSA-CAM module to improve feature representation in cluttered industrial scenes while reducing computational cost is presented.
Longxin Lin, Xin Wang, Deping Li· International journal of pat...· 0 citations
Current object detection models face significant challenges when applied to ultra-high-resolution images, as global downscaling frequently destroys crucial details for small objects, while EGC wastes computation on irrelevant regions and causes object truncation at tile boundaries. We propose a two-step reasoning archi...
Gia-Phuc Song-Dong, Anh-Kiet Tran-Nhu, Minh-Triet Tran et al.· International Conference on...· 0 citations
A lightweight YOLO-style detector that integrates a PP-HGNetV2 tiny backbone, an enhanced normalization-based attention module (ImNAM), and an improved complete intersection-over-union loss (ImCIoU) shows strong potential for intelligent industrial inspection on resource-constrained platforms, subject to further hardwa...
Bangqiang Han, Qing Cheng, Sheng-Bin Wang et al.· Technologies· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
