Skip to main content
Fig. 4 | Journal of Big Data

Fig. 4

From: Domain randomization for neural network classification

Fig. 4

Optimal accuracy of models trained using different synthetic datasets. “Synth” represents the control model trained on domain randomization techniques outlined in Sect.  "Methods/experimental" using dropout. The others represent datasets were a certain parameter was omitted in the data generation processes such as lighting or textures. We also go a step further and texturize the cats and dogs in what is labelled as “texture subject” bar

Back to article page