CAM-YOLO: A Framework for Non-Salient Object Detection by Exploiting Contextual Interdependencies
CAM-YOLO, an enhanced architecture based on YOLOv8 that designs a Contextual Association Module (CAM) that explicitly models long-range spatial dependencies, and integrates a Dual-Branch Attention Mechanism to refine the feature processing flow, thereby strengthening the contextual feature representations crucial for detecting non-salient instances.