Figure 9
From: Adaptive pixel attention network for hyperspectral image classification
OA and AA accuracies obtained by IP, KSC, UP, and HU with different training sample sizes for different methods. (a) IP-OA. (b) KSC-OA. (c) UP-OA. (d) HU-OA. (e) IP-AA. (f) KSC-AA. (g) UP-OA. (h) HU-AA.
