Table 4 Label conversion of orange dataset to apple dataset: for the pseudo label obtained with different confidence thresholds, the pseudo-label self-learning method is further adopted to reduce the influence of noise in the pseudo label and generate a real apple dataset \({\boldsymbol{D}}_{{\boldsymbol{T}}\_{\boldsymbol{apple}}}^{\mathbf{L}}\) with higher quality labels

From: Easy domain adaptation method for filling the species gap in deep learning-based fruit detection