Fig. 1. YOLACT structure diagram

Fig. 2. YOLACTR network structure

Fig. 3. Anchless anchor box example segmentation model structure

Fig. 4. Schematic diagram of the positional embedding

Fig. 5. Structure diagram of mask generation network

Fig. 6. Predictive network structure

Fig. 7. Object detection results

Fig. 8. Instance segmentation detection results

Fig. 9. Loss variation curves under different loss function configurations

Fig. 10. Different curves for 2- and 6-layer Transformer models. (a) Loss variation curves; (b) Accuracy variation curves

Fig. 11. Schematic diagrams of the decline of each loss during the training process. (a) Total loss curve; (b) Classification loss curve; (c) Mask loss curve

Fig. 12. Mask detection accuracy rise graph

Fig. 13. Comparison diagrams before improvement (left) and after improvement (right)

Fig. 14. Comparison diagram of instance segmentation results 1

Fig. 15. Comparison diagram of instance segmentation results 2