diff --git a/torchvision/datasets/coco.py b/torchvision/datasets/coco.py
index 5ce42ddad72..9dd3c7adf85 100644
--- a/torchvision/datasets/coco.py
+++ b/torchvision/datasets/coco.py
@@ -14,6 +14,8 @@ class CocoCaptions(VisionDataset):
             and returns a transformed version. E.g, ``transforms.ToTensor``
         target_transform (callable, optional): A function/transform that takes in the
             target and transforms it.
+        transforms (callable, optional): A function/transform that takes input sample and its target as entry
+            and returns a transformed version.
 
     Example:
 
@@ -86,6 +88,8 @@ class CocoDetection(VisionDataset):
             and returns a transformed version. E.g, ``transforms.ToTensor``
         target_transform (callable, optional): A function/transform that takes in the
             target and transforms it.
+        transforms (callable, optional): A function/transform that takes input sample and its target as entry
+            and returns a transformed version.
     """
 
     def __init__(self, root, annFile, transform=None, target_transform=None, transforms=None):
diff --git a/torchvision/datasets/sbd.py b/torchvision/datasets/sbd.py
index 901e45d0c83..3c9202fdbfd 100644
--- a/torchvision/datasets/sbd.py
+++ b/torchvision/datasets/sbd.py
@@ -36,7 +36,7 @@ class SBDataset(VisionDataset):
         download (bool, optional): If true, downloads the dataset from the internet and
             puts it in root directory. If dataset is already downloaded, it is not
             downloaded again.
-        xy_transform (callable, optional): A function/transform that takes input sample and its target as entry
+        transforms (callable, optional): A function/transform that takes input sample and its target as entry
             and returns a transformed version. Input sample is PIL image and target is a numpy array
             if `mode='boundaries'` or PIL image if `mode='segmentation'`.
     """
diff --git a/torchvision/datasets/voc.py b/torchvision/datasets/voc.py
index 47f28d5c619..390c441911d 100644
--- a/torchvision/datasets/voc.py
+++ b/torchvision/datasets/voc.py
@@ -66,6 +66,8 @@ class VOCSegmentation(VisionDataset):
             and returns a transformed version. E.g, ``transforms.RandomCrop``
         target_transform (callable, optional): A function/transform that takes in the
             target and transforms it.
+        transforms (callable, optional): A function/transform that takes input sample and its target as entry
+            and returns a transformed version.
     """
 
     def __init__(self,
@@ -145,6 +147,8 @@ class VOCDetection(VisionDataset):
             and returns a transformed version. E.g, ``transforms.RandomCrop``
         target_transform (callable, required): A function/transform that takes in the
             target and transforms it.
+        transforms (callable, optional): A function/transform that takes input sample and its target as entry
+            and returns a transformed version.
     """
 
     def __init__(self,