Skip to main content

Table 4 Counting performance with different number of training samples (\(N_{train}\)) on the MTC dataset

From: TasselNet: counting maize tassels in the wild via local counts regression network

\(N_{train}\) MAE MSE
\(2.37\times 10^4\) 9.5 14.2
\(9.13\times 10^4\) 8.5 13.4
\(3.56\times 10^5\) 6.6 9.6
\(1.41\times 10^6\) 6.5 10.8
  1. The performance is averaged over 8 test sequences, and the lowest error is italicised