3A-YOLO: New Real-Time Object Detectors with Triple Discriminative Awareness and Coordinated Representations
This work addresses the need for more accurate real-time object detection in computer vision applications, but it is incremental as it builds on existing YOLO methods with attention enhancements.
The paper tackles the problem of improving real-time object detectors by proposing 3A-YOLO, which uses hierarchical attention mechanisms to enhance discriminative awareness and coordinated representations, resulting in effective performance on COCO and VOC benchmarks.
Recent research on real-time object detectors (e.g., YOLO series) has demonstrated the effectiveness of attention mechanisms for elevating model performance. Nevertheless, existing methods neglect to unifiedly deploy hierarchical attention mechanisms to construct a more discriminative YOLO head which is enriched with more useful intermediate features. To tackle this gap, this work aims to leverage multiple attention mechanisms to hierarchically enhance the triple discriminative awareness of the YOLO detection head and complementarily learn the coordinated intermediate representations, resulting in a new series detectors denoted 3A-YOLO. Specifically, we first propose a new head denoted TDA-YOLO Module, which unifiedly enhance the representations learning of scale-awareness, spatial-awareness, and task-awareness. Secondly, we steer the intermediate features to coordinately learn the inter-channel relationships and precise positional information. Finally, we perform neck network improvements followed by introducing various tricks to boost the adaptability of 3A-YOLO. Extensive experiments across COCO and VOC benchmarks indicate the effectiveness of our detectors.