1. What have the authors stated for future works in "Quantification-oriented learning based on reliable classifiers" ?
From this point of view, the authors strongly believe that the methods presented here should be considered for future studies in the field of quantification.. 1. 3. Thus, these methods may be considered variants of CC, which can be further improved with similar strategies to those applied in AC, Max, X, MS and T50.. As a rule of thumb, the authors suggest = 2, because, in line with the discussion of Figure 4 and the analysis of the empirical results, it effectively combines the best features of both components.
read more
2. What contributions have the authors mentioned in the paper "Quantification-oriented learning based on reliable classifiers" ?
Moreover, current quantification models based on classifiers present the drawback of being trained with loss functions aimed at classification rather than quantification.. This paper presents a learning method that optimizes an alternative metric that combines simultaneously quantification and classification performance.
read more
