Macro-Average Accuracy
An aggregate metric for classification tasks that first computes the accuracy of each class and then takes the arithmetic mean; it is more sensitive to the performance of minority classes and is suited to class-imbalanced settings.
Timeline (last 90 days)
On the Mixed-WM38 dataset (containing 6,866 wafer maps), the multi-region prompting strategy achieved 92.9% macro-average accuracy and 93.8% overall accuracy.
Macro-average accuracy first computes the accuracy of each class separately and then takes the arithmetic mean, making it more sensitive to the performance of minority classes; overall accuracy is the proportion of all samples predicted correctly and is easily affected by the class sample size distribution.
Macro-average accuracy is a metric that first computes the accuracy of each task separately and then takes the arithmetic mean over tasks, giving each task equal weight.
All Facts (3)
On the Mixed-WM38 dataset (containing 6,866 wafer maps), the multi-region prompting strategy achieved 92.9% macro-average accuracy and 93.8% overall accuracy.
50%UnverifiedMacro-average accuracy first computes the accuracy of each class separately and then takes the arithmetic mean, making it more sensitive to the performance of minority classes; overall accuracy is the proportion of all samples predicted correctly and is easily affected by the class sample size distribution.
50%UnverifiedMacro-average accuracy is a metric that first computes the accuracy of each task separately and then takes the arithmetic mean over tasks, giving each task equal weight.
50%