Figures & data
Figure 3. IA generated common features, including Attention Generation and Inverted Attention to Generate Common Features.
![Figure 3. IA generated common features, including Attention Generation and Inverted Attention to Generate Common Features.](/cms/asset/851fce7a-8de4-467d-9432-f9859ebcb108/ccos_a_2173145_f0003_oc.jpg)
Figure 6. (a): The distribution of common features in 2D space in normal circumstances (b): The distribution of common features generated by IA in 2D space
![Figure 6. (a): The distribution of common features in 2D space in normal circumstances (b): The distribution of common features generated by IA in 2D space](/cms/asset/41c2f090-14de-4fd4-9240-41edd4b900a3/ccos_a_2173145_f0006_oc.jpg)
Figure 7. (a): Visualisation of the common features and text features of CNN, IAO, and IAOPM in 2D space. (b): Visualisation of the common features (different classes) of IAO, IAOPM, and FP-Net in 2D space.
![Figure 7. (a): Visualisation of the common features and text features of CNN, IAO, and IAOPM in 2D space. (b): Visualisation of the common features (different classes) of IAO, IAOPM, and FP-Net in 2D space.](/cms/asset/d6afbe0c-c6b4-47a0-a647-de1682a03871/ccos_a_2173145_f0007_oc.jpg)
Table
Table 1. Parameter settings of feature extractors.
Table 2. Results of IAOPM, Self-Attention and FP-Net for four benchmark datasets.
Table 3. Time overhead table.
Figure 8. The visualisation of common features in 2D and polar coordinate space for IAOPM and FP-Net.
![Figure 8. The visualisation of common features in 2D and polar coordinate space for IAOPM and FP-Net.](/cms/asset/4e46aef0-d2b7-4abe-8535-88013dd0daa1/ccos_a_2173145_f0008_oc.jpg)
Table 4. Ablation experiments.
Table 5. Hyperparametric experiment.