diff --git a/chainercv/datasets/__init__.py b/chainercv/datasets/__init__.py
index 58b6d1b6a1..51738f01fd 100644
--- a/chainercv/datasets/__init__.py
+++ b/chainercv/datasets/__init__.py
@@ -1,3 +1,7 @@
+from chainercv.datasets.ade20k.ade20k_semantic_segmentation_dataset import ADE20KSemanticSegmentationDataset  # NOQA
+from chainercv.datasets.ade20k.ade20k_test_image_dataset import ADE20KTestImageDataset  # NOQA
+from chainercv.datasets.ade20k.ade20k_utils import ade20k_semantic_segmentation_label_colors  # NOQA
+from chainercv.datasets.ade20k.ade20k_utils import ade20k_semantic_segmentation_label_names  # NOQA
 from chainercv.datasets.camvid.camvid_dataset import camvid_ignore_label_color  # NOQA
 from chainercv.datasets.camvid.camvid_dataset import camvid_label_colors  # NOQA
 from chainercv.datasets.camvid.camvid_dataset import camvid_label_names  # NOQA
diff --git a/chainercv/datasets/ade20k/__init__.py b/chainercv/datasets/ade20k/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/chainercv/datasets/ade20k/ade20k_semantic_segmentation_dataset.py b/chainercv/datasets/ade20k/ade20k_semantic_segmentation_dataset.py
new file mode 100644
index 0000000000..2d2cd73320
--- /dev/null
+++ b/chainercv/datasets/ade20k/ade20k_semantic_segmentation_dataset.py
@@ -0,0 +1,75 @@
+import glob
+import os
+
+import numpy as np
+
+from chainer import dataset
+from chainercv.utils import read_image
+
+from chainercv.datasets.ade20k.ade20k_utils import get_ade20k
+
+
+root = 'pfnet/chainercv/ade20k'
+url = 'http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip'
+
+
+class ADE20KSemanticSegmentationDataset(dataset.DatasetMixin):
+
+    """Semantic segmentation dataset for `ADE20K`_.
+
+    This is ADE20K dataset distributed in MIT Scene Parsing Benchmark website.
+    It has 20,210 training images and 2,000 validation images.
+
+    .. _`MIT Scene Parsing Benchmark`: http://sceneparsing.csail.mit.edu/
+
+    Args:
+        data_dir (string): Path to the dataset directory. The directory should
+            contain the :obj:`ADEChallengeData2016` directory. And that
+            directory should contain at least :obj:`images` and
+            :obj:`annotations` directries. If :obj:`auto` is given, the dataset
+            is automatically downloaded into
+            :obj:`$CHAINER_DATASET_ROOT/pfnet/chainercv/ade20k`.
+        split ({'train', 'val'}): Select from dataset splits used in
+            MIT Scene Parsing Benchmark dataset (ADE20K).
+
+    """
+
+    def __init__(self, data_dir='auto', split='train'):
+        if data_dir is 'auto':
+            data_dir = get_ade20k(root, url)
+
+        if split == 'train' or split == 'val':
+            img_dir = os.path.join(
+                data_dir, 'ADEChallengeData2016', 'images',
+                'training' if split == 'train' else 'validation')
+            label_dir = os.path.join(
+                data_dir, 'ADEChallengeData2016', 'annotations',
+                'training' if split == 'train' else 'validation')
+        else:
+            raise ValueError(
+                'Please give \'split\' argument with either \'train\' or '
+                '\'val\'.')
+
+        self.img_paths = sorted(glob.glob(os.path.join(img_dir, '*.jpg')))
+        self.label_paths = sorted(glob.glob(os.path.join(label_dir, '*.png')))
+
+    def __len__(self):
+        return len(self.img_paths)
+
+    def get_example(self, i):
+        """Returns the i-th example.
+
+        Args:
+            i (int): The index of the example.
+
+        Returns:
+            Returns a tuple consited of a color image and a label whose shapes
+            are (3, H, W) and (H, W), respectively. H and W are height and
+            width of the image. The dtype of the color image is
+            :obj:`numpy.float32` and the dtype of the label image is
+            :obj:`numpy.int32`.
+
+        """
+        img = read_image(self.img_paths[i])
+        label = read_image(self.label_paths[i], dtype=np.int32, color=False)[0]
+        return img, label
diff --git a/chainercv/datasets/ade20k/ade20k_test_image_dataset.py b/chainercv/datasets/ade20k/ade20k_test_image_dataset.py
new file mode 100644
index 0000000000..92984fab9a
--- /dev/null
+++ b/chainercv/datasets/ade20k/ade20k_test_image_dataset.py
@@ -0,0 +1,52 @@
+import glob
+import os
+
+from chainer import dataset
+from chainercv.utils import read_image
+
+from chainercv.datasets.ade20k.ade20k_utils import get_ade20k
+
+
+root = 'pfnet/chainercv/ade20k'
+url = 'http://data.csail.mit.edu/places/ADEchallenge/release_test.zip'
+
+
+class ADE20KTestImageDataset(dataset.DatasetMixin):
+
+    """Image dataset for test split of `ADE20K`_.
+
+    This is an image dataset of test split in ADE20K dataset distributed at
+    MIT Scene Parsing Benchmark website. It has 3,352 test images.
+
+    .. _`MIT Scene Parsing Benchmark`: http://sceneparsing.csail.mit.edu/
+
+    Args:
+        data_dir (string): Path to the dataset directory. The directory should
+            contain the :obj:`release_test` dir. If :obj:`auto` is given, the
+            dataset is automatically downloaded into
+            :obj:`$CHAINER_DATASET_ROOT/pfnet/chainercv/ade20k`.
+
+    """
+
+    def __init__(self, data_dir='auto'):
+        if data_dir is 'auto':
+            data_dir = get_ade20k(root, url)
+        img_dir = os.path.join(data_dir, 'release_test', 'testing')
+        self.img_paths = sorted(glob.glob(os.path.join(img_dir, '*.jpg')))
+
+    def __len__(self):
+        return len(self.img_paths)
+
+    def get_example(self, i):
+        """Returns the i-th example.
+
+        Args:
+            i (int): The index of the example.
+
+        Returns:
+            Returns a color image whose shape is (3, H, W). H and W are height
+            and width of the image. The dtype of the image is
+            :obj:`numpy.float32`.
+
+        """
+        return read_image(self.img_paths[i])
diff --git a/chainercv/datasets/ade20k/ade20k_utils.py b/chainercv/datasets/ade20k/ade20k_utils.py
new file mode 100644
index 0000000000..9ac702edfe
--- /dev/null
+++ b/chainercv/datasets/ade20k/ade20k_utils.py
@@ -0,0 +1,321 @@
+# The values used here are copied from CSAILVision/sceneparsing:
+# https://github.com/CSAILVision/sceneparsing
+
+import os
+
+from chainer.dataset import download
+from chainercv import utils
+
+
+def get_ade20k(root, url):
+    data_root = download.get_dataset_directory(root)
+    cache_path = utils.cached_download(url)
+    utils.extractall(cache_path, data_root, os.path.splitext(url)[1])
+    return data_root
+
+
+ade20k_semantic_segmentation_label_names = (
+    'wall',
+    'edifice',
+    'sky',
+    'flooring',
+    'tree',
+    'ceiling',
+    'route',
+    'bed ',
+    'window ',
+    'grass',
+    'cabinet',
+    'pavement',
+    'soul',
+    'ground',
+    'door',
+    'table',
+    'mount',
+    'life',
+    'pall',
+    'chair',
+    'motorcar',
+    'water',
+    'picture',
+    'lounge',
+    'shelf',
+    'house',
+    'sea',
+    'mirror',
+    'carpeting',
+    'field',
+    'armchair',
+    'seat',
+    'fencing',
+    'desk',
+    'stone',
+    'press',
+    'lamp',
+    'tub',
+    'rail',
+    'cushion',
+    'stand',
+    'box',
+    'pillar',
+    'sign',
+    'dresser',
+    'counter',
+    'sand',
+    'sink',
+    'skyscraper',
+    'fireplace',
+    'icebox',
+    'stand',
+    'path',
+    'steps',
+    'runway',
+    'vitrine',
+    'table',
+    'pillow',
+    'screen',
+    'staircase',
+    'river',
+    'span',
+    'bookcase',
+    'screen',
+    'table',
+    'throne',
+    'flower',
+    'book',
+    'hill',
+    'bench',
+    'countertop',
+    'stove',
+    'tree',
+    'island',
+    'system',
+    'chair',
+    'boat',
+    'bar',
+    'machine',
+    'shanty',
+    'vehicle',
+    'towel',
+    'source',
+    'motortruck',
+    'tower',
+    'pendent',
+    'sunblind',
+    'lamp',
+    'kiosk',
+    'box',
+    'plane',
+    'track',
+    'clothes',
+    'pole',
+    'soil',
+    'handrail',
+    'stairway',
+    'hassock',
+    'bottle',
+    'sideboard',
+    'card',
+    'stage',
+    'van',
+    'ship',
+    'fountain',
+    'transporter',
+    'canopy',
+    'machine',
+    'toy',
+    'natatorium',
+    'stool',
+    'cask',
+    'handbasket',
+    'falls',
+    'shelter',
+    'bag',
+    'motorbike',
+    'cradle',
+    'oven',
+    'ball',
+    'food',
+    'stair',
+    'tank',
+    'marque',
+    'oven',
+    'flowerpot',
+    'fauna',
+    'cycle ',
+    'lake',
+    'machine',
+    'screen',
+    'cover',
+    'sculpture',
+    'hood',
+    'sconce',
+    'vase',
+    'stoplight',
+    'tray',
+    'bin',
+    'fan',
+    'dock',
+    'screen',
+    'plate',
+    'device',
+    'board',
+    'shower',
+    'radiator',
+    'glass',
+    'clock',
+    'flag'
+)
+
+ade20k_semantic_segmentation_label_colors = (
+    (120, 120, 120),
+    (180, 120, 120),
+    (6, 230, 230),
+    (80, 50, 50),
+    (4, 200, 3),
+    (120, 120, 80),
+    (140, 140, 140),
+    (204, 5, 255),
+    (230, 230, 230),
+    (4, 250, 7),
+    (224, 5, 255),
+    (235, 255, 7),
+    (150, 5, 61),
+    (120, 120, 70),
+    (8, 255, 51),
+    (255, 6, 82),
+    (143, 255, 140),
+    (204, 255, 4),
+    (255, 51, 7),
+    (204, 70, 3),
+    (0, 102, 200),
+    (61, 230, 250),
+    (255, 6, 51),
+    (11, 102, 255),
+    (255, 7, 71),
+    (255, 9, 224),
+    (9, 7, 230),
+    (220, 220, 220),
+    (255, 9, 92),
+    (112, 9, 255),
+    (8, 255, 214),
+    (7, 255, 224),
+    (255, 184, 6),
+    (10, 255, 71),
+    (255, 41, 10),
+    (7, 255, 255),
+    (224, 255, 8),
+    (102, 8, 255),
+    (255, 61, 6),
+    (255, 194, 7),
+    (255, 122, 8),
+    (0, 255, 20),
+    (255, 8, 41),
+    (255, 5, 153),
+    (6, 51, 255),
+    (235, 12, 255),
+    (160, 150, 20),
+    (0, 163, 255),
+    (140, 140, 140),
+    (250, 10, 15),
+    (20, 255, 0),
+    (31, 255, 0),
+    (255, 31, 0),
+    (255, 224, 0),
+    (153, 255, 0),
+    (0, 0, 255),
+    (255, 71, 0),
+    (0, 235, 255),
+    (0, 173, 255),
+    (31, 0, 255),
+    (11, 200, 200),
+    (255, 82, 0),
+    (0, 255, 245),
+    (0, 61, 255),
+    (0, 255, 112),
+    (0, 255, 133),
+    (255, 0, 0),
+    (255, 163, 0),
+    (255, 102, 0),
+    (194, 255, 0),
+    (0, 143, 255),
+    (51, 255, 0),
+    (0, 82, 255),
+    (0, 255, 41),
+    (0, 255, 173),
+    (10, 0, 255),
+    (173, 255, 0),
+    (0, 255, 153),
+    (255, 92, 0),
+    (255, 0, 255),
+    (255, 0, 245),
+    (255, 0, 102),
+    (255, 173, 0),
+    (255, 0, 20),
+    (255, 184, 184),
+    (0, 31, 255),
+    (0, 255, 61),
+    (0, 71, 255),
+    (255, 0, 204),
+    (0, 255, 194),
+    (0, 255, 82),
+    (0, 10, 255),
+    (0, 112, 255),
+    (51, 0, 255),
+    (0, 194, 255),
+    (0, 122, 255),
+    (0, 255, 163),
+    (255, 153, 0),
+    (0, 255, 10),
+    (255, 112, 0),
+    (143, 255, 0),
+    (82, 0, 255),
+    (163, 255, 0),
+    (255, 235, 0),
+    (8, 184, 170),
+    (133, 0, 255),
+    (0, 255, 92),
+    (184, 0, 255),
+    (255, 0, 31),
+    (0, 184, 255),
+    (0, 214, 255),
+    (255, 0, 112),
+    (92, 255, 0),
+    (0, 224, 255),
+    (112, 224, 255),
+    (70, 184, 160),
+    (163, 0, 255),
+    (153, 0, 255),
+    (71, 255, 0),
+    (255, 0, 163),
+    (255, 204, 0),
+    (255, 0, 143),
+    (0, 255, 235),
+    (133, 255, 0),
+    (255, 0, 235),
+    (245, 0, 255),
+    (255, 0, 122),
+    (255, 245, 0),
+    (10, 190, 212),
+    (214, 255, 0),
+    (0, 204, 255),
+    (20, 0, 255),
+    (255, 255, 0),
+    (0, 153, 255),
+    (0, 41, 255),
+    (0, 255, 204),
+    (41, 0, 255),
+    (41, 255, 0),
+    (173, 0, 255),
+    (0, 245, 255),
+    (71, 0, 255),
+    (122, 0, 255),
+    (0, 255, 184),
+    (0, 92, 255),
+    (184, 255, 0),
+    (0, 133, 255),
+    (255, 214, 0),
+    (25, 194, 194),
+    (102, 255, 0),
+    (92, 0, 255)
+)
diff --git a/docs/source/reference/datasets.rst b/docs/source/reference/datasets.rst
index ba3f9b5f18..e305719718 100644
--- a/docs/source/reference/datasets.rst
+++ b/docs/source/reference/datasets.rst
@@ -18,6 +18,17 @@ TransformDataset
 ~~~~~~~~~~~~~~~~
 .. autoclass:: TransformDataset
 
+ADE20K
+------
+
+ADE20KSemanticSegmentationDataset
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+.. autoclass:: ADE20KSemanticSegmentationDataset
+
+ADE20KTestImageDataset
+~~~~~~~~~~~~~~~~~~~~~~
+.. autoclass:: ADE20KTestImageDataset
+
 CamVid
 ------
 
diff --git a/tests/datasets_tests/ade20k_tests/test_ade20k.py b/tests/datasets_tests/ade20k_tests/test_ade20k.py
new file mode 100644
index 0000000000..bb2a8dfc95
--- /dev/null
+++ b/tests/datasets_tests/ade20k_tests/test_ade20k.py
@@ -0,0 +1,43 @@
+import unittest
+
+from chainer import testing
+from chainer.testing import attr
+import numpy as np
+
+from chainercv.datasets import ade20k_semantic_segmentation_label_names
+from chainercv.datasets import ADE20KSemanticSegmentationDataset
+from chainercv.datasets import ADE20KTestImageDataset
+from chainercv.utils import assert_is_semantic_segmentation_dataset
+from chainercv.utils.testing.assertions.assert_is_image import assert_is_image
+
+
+@testing.parameterize(
+    {'split': 'train'},
+    {'split': 'val'},
+)
+class TestADE20KSemanticSegmentationDataset(unittest.TestCase):
+
+    def setUp(self):
+        self.dataset = ADE20KSemanticSegmentationDataset(split=self.split)
+
+    @attr.slow
+    def test_ade20k_dataset(self):
+        assert_is_semantic_segmentation_dataset(
+            self.dataset, len(ade20k_semantic_segmentation_label_names),
+            n_example=10)
+
+
+class TestADE20KTestImageDataset(unittest.TestCase):
+
+    def setUp(self):
+        self.dataset = ADE20KTestImageDataset()
+
+    @attr.slow
+    def test_ade20k_dataset(self):
+        indices = np.random.permutation(np.arange(len(self.dataset)))
+        for i in indices[:10]:
+            img = self.dataset[i]
+            assert_is_image(img, color=True)
+
+
+testing.run_module(__name__, __file__)