NICO dataset

下载 [大小]：8.22G [链接]：https://pan.baidu.com/s/1sOwi-_19zvJpr7wf8QNFFw [提取码]：ev5n

 

样本图片

Animals

Vehicle

Overview

NICO dataset is dedicatedly designed for Non-I.I.D. or OOD (Out-of-Distribution) image classification. It simulates a real world setting that the testing distribution may induce arbitrary shifting from the training distribution, which violates the traditional I.I.D. hypothesis of most ML methods. The typical research directions that the dataset can well support include but are not limited to transfer learning or domain adaptation (when testing distribution is known) and stable learning or domain generalization (when testing distribution is unknown).
The basic idea of constructing the dataset is to label images with both main concepts (e.g. dog) and the contexts (e.g. on grass) that visual concepts appear in. By adjusting the proportions of different contexts in training and testing data, one can control the degree of distribution shift flexibly and conduct studies on different kinds of Non-I.I.D. settings.
Till now, there are two superclasses: Animal and Vehicle, with 10 classes for Animal and 9 classes for Vehicle. Each class has 9 or 10 contexts. The average number of images per context ranges from 83 to 215, and the average number of images per class is about 1300 images (similar to ImageNet). In total, NICO contains 19 classes, 188 contexts and nearly 25,000 images. The current version has been able to support the training of deep convolution networks (e.g. ResNet-18) from scratch. The scale is still increasing, and is easy to be expanded because of the hierarchical structure.

Data Format

The hierarchical structure is shown as below:

G:\shannon\deeplearning_dataset\NICO>tree
卷 study_work 的文件夹 PATH 列表
卷序列号为 E836-4D9C
G:.
├─NICO_Animal
│  └─Animal
│      ├─bear
│      │  ├─black
│      │  ├─brown
│      │  ├─eating grass
│      │  ├─in forest
│      │  ├─in water
│      │  ├─lying
│      │  ├─on ground
│      │  ├─on snow
│      │  ├─on tree
│      │  └─white
│      ├─bird
│      │  ├─eating
│      │  ├─flying
│      │  ├─in cage
│      │  ├─in hand
│      │  ├─in water
│      │  ├─on branch
│      │  ├─on grass
│      │  ├─on ground
│      │  ├─on shoulder
│      │  └─standing
│      ├─cat
│      │  ├─at home
│      │  ├─eating
│      │  ├─in cage
│      │  ├─in river
│      │  ├─in street
│      │  ├─in water
│      │  ├─on grass
│      │  ├─on snow
│      │  ├─on tree
│      │  └─walking
│      ├─cow
│      │  ├─aside people
│      │  ├─at home
│      │  ├─eating
│      │  ├─in forest
│      │  ├─in river
│      │  ├─lying
│      │  ├─on grass
│      │  ├─on snow
│      │  ├─spotted
│      │  └─standing
│      ├─dog
│      │  ├─at home
│      │  ├─eating
│      │  ├─in cage
│      │  ├─in street
│      │  ├─in water
│      │  ├─lying
│      │  ├─on beach
│      │  ├─on grass
│      │  ├─on snow
│      │  └─running
│      ├─elephant
│      │  ├─eating
│      │  ├─in circus
│      │  ├─in forest
│      │  ├─in river
│      │  ├─in street
│      │  ├─in zoo
│      │  ├─lying
│      │  ├─on grass
│      │  ├─on snow
│      │  └─standing
│      ├─horse
│      │  ├─aside people
│      │  ├─at home
│      │  ├─in forest
│      │  ├─in river
│      │  ├─in street
│      │  ├─lying
│      │  ├─on beach
│      │  ├─on grass
│      │  ├─on snow
│      │  └─running
│      ├─monkey
│      │  ├─climbing
│      │  ├─eating
│      │  ├─in cage
│      │  ├─in forest
│      │  ├─in water
│      │  ├─on beach
│      │  ├─on grass
│      │  ├─on snow
│      │  ├─sitting
│      │  └─walking
│      ├─rat
│      │  ├─at home
│      │  ├─eating
│      │  ├─in cage
│      │  ├─in forest
│      │  ├─in hole
│      │  ├─in water
│      │  ├─lying
│      │  ├─on grass
│      │  ├─on snow
│      │  └─running
│      └─sheep
│          ├─aside people
│          ├─at sunset
│          ├─eating
│          ├─in forest
│          ├─in water
│          ├─lying
│          ├─on grass
│          ├─on road
│          ├─on snow
│          └─walking
└─NICO_Vehicle
    └─Vehicle
        ├─airplane
        │  ├─around cloud
        │  ├─aside mountain
        │  ├─at airport
        │  ├─at night
        │  ├─in city
        │  ├─in sunrise
        │  ├─on beach
        │  ├─on grass
        │  ├─taking off
        │  └─with pilot
        ├─bicycle
        │  ├─in garage
        │  ├─in street
        │  ├─in sunset
        │  ├─on beach
        │  ├─on grass
        │  ├─on road
        │  ├─on snow
        │  ├─shared
        │  ├─velodrome
        │  └─with people
        ├─boat
        │  ├─at wharf
        │  ├─cross bridge
        │  ├─in city
        │  ├─in river
        │  ├─in sunset
        │  ├─on beach
        │  ├─sailboat
        │  ├─with people
        │  ├─wooden
        │  └─yacht
        ├─bus
        │  ├─aside traffic light
        │  ├─aside tree
        │  ├─at station
        │  ├─at yard
        │  ├─double decker
        │  ├─in city
        │  ├─on bridge
        │  ├─on snow
        │  └─with people
        ├─car
        │  ├─at park
        │  ├─in city
        │  ├─in sunset
        │  ├─on beach
        │  ├─on booth
        │  ├─on bridge
        │  ├─on road
        │  ├─on snow
        │  ├─on track
        │  └─with people
        ├─helicopter
        │  ├─aside mountain
        │  ├─at heliport
        │  ├─in city
        │  ├─in forest
        │  ├─in sunset
        │  ├─on beach
        │  ├─on grass
        │  ├─on sea
        │  ├─on snow
        │  └─with people
        ├─motorcycle
        │  ├─in city
        │  ├─in garage
        │  ├─in street
        │  ├─in sunset
        │  ├─on beach
        │  ├─on grass
        │  ├─on road
        │  ├─on snow
        │  ├─on track
        │  └─with people
        ├─train
        │  ├─aside mountain
        │  ├─at station
        │  ├─cross tunnel
        │  ├─in forest
        │  ├─in sunset
        │  ├─on beach
        │  ├─on bridge
        │  ├─on snow
        │  └─subway
        └─truck
            ├─aside mountain
            ├─in city
            ├─in forest
            ├─in race
            ├─in sunset
            ├─on beach
            ├─on bridge
            ├─on grass
            ├─on road
            └─on snow

Citation

Please use the following citation when referencing the dataset:

@inproceedings{Johnson10,
   title = {Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation},
   author = {Johnson, Sam and Everingham, Mark},
   year = {2010},
   booktitle = {Proceedings of the British Machine Vision Conference},
   note = {doi:10.5244/C.24.12}
}