The I.I.D. hypothesis between training data and testing data is the basis of a large number of image classification methods. Such a property can hardly be guaranteed in practical cases where the Non-IIDness is common, leading to instable performances of these models. In literature, however, the Non-I.I.D. image classification problem is largely understudied. A key reason is the lacking of a well-designed dataset to support related research. In this paper, we construct and release a Non-I.I.D. image dataset called NICO, which makes use of contexts to create Non-IIDness consciously. Extended experimental results and anslyses demonstrate that the NICO dataset can well support the training of a ConvNet model from scratch, and NICO can support various Non-I.I.D. situations with sufficient flexibility compared to other datasets.
[1]
Fei-Fei Li,et al.
ImageNet: A large-scale hierarchical image database
,
2009,
2009 IEEE Conference on Computer Vision and Pattern Recognition.
[2]
Luc Van Gool,et al.
The Pascal Visual Object Classes Challenge: A Retrospective
,
2014,
International Journal of Computer Vision.
[3]
Kaiming He,et al.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
,
2015,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[4]
Mark E. J. Newman,et al.
Power-Law Distributions in Empirical Data
,
2007,
SIAM Rev..
[5]
Andrew Zisserman,et al.
Very Deep Convolutional Networks for Large-Scale Image Recognition
,
2014,
ICLR.
[6]
Alexei A. Efros,et al.
Unbiased look at dataset bias
,
2011,
CVPR 2011.