Open Set Sheep Face Recognition Based on Euclidean Space Metric

Figure 10

Center loss: (a) For image features extracted by the model, the intraclass distance is even greater than the interclass distance (b). (c) represents the feature description learned under the center loss supervised training. The sample features are close to the center of the class, compact within the class, and separated between classes.

(a)

(b)

(c)