Dual-attention guided one-shot ore detection with classification loss enhancement

In ore particle size detection, traditional object detectors often suffer from high computational cost and limited classification capability. Few-shot object detection algorithms alleviate these issues by reducing data requirements and enhancing generalization. Building upon this, one-shot object detection offers greater flexibility, enabling rapid adaptation to new ore samples. In this study, we propose a dual-attention guided detector with enhanced classification supervision specifically optimized for ore particle size detection. The detector integrates contextual and channel attention mechanisms to enable multi-dimensional dynamic modeling of the input, significantly improving feature extraction from limited ore samples—particularly in fine-grained detection tasks. Moreover, we introduce an auxiliary classification design that encourages the network to learn more diverse and discriminative representations, thereby improving category discrimination under extremely limited supervision. Notably, our detector achieves an average precision of 46.8 percent under the one-shot fine-tuning setting, operates in real time at 48 frames per second, and has a compact model size of 16.1 megabytes. These results indicate that the proposed method provides an effective and lightweight solution for ore detection under scarce-annotation conditions in the tested single-class setting.