[Retracted] Advances in Hyperspectral Image Classification with a Bottleneck Attention Mechanism Based on 3D-FCNN Model and Imaging Spectrometer Sensor

Figure 14

Classification effect diagrams of the SV dataset of different modules: (a) Ground truth; (b) 3D-FCNN; (c) SE+3D-FCNN; (d) BandAM+3D-FCNN; and (e) BAM+3D-FCNN.Tables 5 and 6 indicate that the proposed BAM considers spatial and spectral information, and it significantly improves classification performance. The 2–3% improvement in each standard demonstrates that the proposed BAM is effective. For HSI classification, the proposed BAM can be considered a plug-and-play supplementary module for most mainstream CNNs.

(a)

(b)

(c)

(d)

(e)