YOLO-MSA: A Multiscale Stereoscopic Attention Network for Empty-Dish Recycling Robots

As the global population ages and the labor force shrinks, using Artificial Intelligence (AI) technology to promote labor productivity growth has become a hot topic. The emergence of Empty-Dish Recycling Robots has effectively alleviated the impact of the decline in labor productivity. This paper proposes a Multi-scale Stereoscopic Attention (MSA) network YOLO-MSA to detect postprandial dishes for Empty-Dish Recycling Robots. First, the standard convolution is replaced with a Res2Net module, which improves the multi-scale expressiveness of the network at a finer-grained level. Second, we adopt a Res2Net with different dilation rates and a novel stereoscopic attention mechanism to propose an MSA module, which is used for coarse-grained multi-scale expression. Thirdly, for multi-scale feature learning in the dimensionality reduction process, a Dimension Reduction Spatial Pyramid Pooling (DRSPP) is proposed to fuse feature maps of different scales. Extensive experiments demonstrate the effectiveness of the proposed MSA module for multi-scale feature learning. Furthermore, YOLO-MSA has achieved 98.47% mean Average Precision ( mAP ) on Dish-21, a dataset of the postprandial dishes, which is much higher than other state-of-the-art models, and has achieved an inference speed of 33.93 frames per second ( FPS ), which meets the needs of real-time detection of the postprandial dish for the Empty-Dish Recycling Robot. Test results on other public datasets show that the proposed YOLO-MSA has a better generalization ability. In summary, YOLO-MSA exhibits satisfactory multi-scale feature expression ability, demonstrates effectiveness and robustness in postprandial dish detection, and has far-reaching significance for the development of Empty-Dish Recycling Robots.