Regular Articles

Fine-grained representation learning in convolutional autoencoders

[+] Author Affiliations
Chang Luo, Jie Wang

Air Force Engineering University, Air and Missile Defense College, No. 1 East Changle Road, Xi’an CN 710051, China

J. Electron. Imaging. 25(2), 023018 (Apr 12, 2016). doi:10.1117/1.JEI.25.2.023018
History: Received January 19, 2016; Accepted March 18, 2016
Text Size: A A A

Abstract.  Convolutional autoencoders (CAEs) have been widely used as unsupervised feature extractors for high-resolution images. As a key component in CAEs, pooling is a biologically inspired operation to achieve scale and shift invariances, and the pooled representation directly affects the CAEs’ performance. Fine-grained pooling, which uses small and dense pooling regions, encodes fine-grained visual cues and enhances local characteristics. However, it tends to be sensitive to spatial rearrangements. In most previous works, pooled features were obtained by empirically modulating parameters in CAEs. We see the CAE as a whole and propose a fine-grained representation learning law to extract better fine-grained features. This representation learning law suggests two directions for improvement. First, we probabilistically evaluate the discrimination-invariance tradeoff with fine-grained granularity in the pooled feature maps, and suggest the proper filter scale in the convolutional layer and appropriate whitening parameters in preprocessing step. Second, pooling approaches are combined with the sparsity degree in pooling regions, and we propose the preferable pooling approach. Experimental results on two independent benchmark datasets demonstrate that our representation learning law could guide CAEs to extract better fine-grained features and performs better in multiclass classification task. This paper also provides guidance for selecting appropriate parameters to obtain better fine-grained representation in other convolutional neural networks.

© 2016 SPIE and IS&T


Chang Luo and Jie Wang
"Fine-grained representation learning in convolutional autoencoders", J. Electron. Imaging. 25(2), 023018 (Apr 12, 2016). ;

Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Convolution Neural Networks with Two Pathways for Image Style Recognition. IEEE Trans Image Process Published online Jun 09, 2017;
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via