diff --git a/mmeval/segmentation/mean_iou.py b/mmeval/segmentation/mean_iou.py
index ce4ac4ab..4f3f089a 100644
--- a/mmeval/segmentation/mean_iou.py
+++ b/mmeval/segmentation/mean_iou.py
@@ -20,9 +20,9 @@ class MeanIoU(BaseMetric):
     In addition to mean iou, it will also compute and return accuracy, mean
     accuracy, mean dice, mean precision, mean recall and mean f-score.
 
-    Currently, there are 2 implementations of this metric: NumPy and PyTorch.
-    Which implementation to use is determined by the type of the calling
-    parameters. e.g. `numpy.ndarray` or `torch.Tensor`.
+    This metric supports 2 kinds of inputs, i.e. ``numpy.ndarray`` and
+    ``torch.Tensor``, and the implementation for the calculation depends on
+    the inputs type.
 
     Args:
         num_classes (int, optional): The number of classes. If None, it will be