Rectifying Transformation Networks for Transformation-Invariant Representations with Power Law

Chunxiao FAN  Yang LI  Lei TIAN  Yong LI  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.3   pp.675-679
Publication Date: 2019/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8112
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
convolutional neural network,  deep learning,  image representation,  transformation error,  

Full Text: PDF(196.7KB)
>>Buy this Article

This letter proposes a representation learning framework of convolutional neural networks (Convnets) that aims to rectify and improve the feature representations learned by existing transformation-invariant methods. The existing methods usually encode feature representations invariant to a wide range of spatial transformations by augmenting input images or transforming intermediate layers. Unfortunately, simply transforming the intermediate feature maps may lead to unpredictable representations that are ineffective in describing the transformed features of the inputs. The reason is that the operations of convolution and geometric transformation are not exchangeable in most cases and so exchanging the two operations will yield the transformation error. The error may potentially harm the performance of the classification networks. Motivated by the fractal statistics of natural images, this letter proposes a rectifying transformation operator to minimize the error. The proposed method is differentiable and can be inserted into the convolutional architecture without making any modification to the optimization algorithm. We show that the rectified feature representations result in better classification performance on two benchmarks.