AttYOLO: A model for object detection

As a fundamental task in computer vision, object detection serves as critical infrastructure for advanced image understanding by providing structured localization and classification data. Addressing the limitation of existing lightweight models in feature representation within complex scenarios, this study proposes an enhanced architecture based on YOLOv7-tiny. The integration of Efficient Channel Attention (ECA) modules establishes cross-channel interaction mechanisms, which significantly improves discriminative feature capture while preserving real-time inference capabilities. Experimental results demonstrate a $1.1 \%$ absolute improvement in mAP metrics on coco dataset, offering a novel technical solution for high-precision real-time detection on embedded systems.