Authors:
Tiziano Portenier
1
;
Qiyang Hu
1
;
Paolo Favaro
1
and
Matthias Zwicker
2
Affiliations:
1
University of Bern, Switzerland
;
2
University of Maryland, United States
Keyword(s):
Image Retrieval, Deep Learning, Autoencoders.
Abstract:
In this paper we develop a representation for fine-grained retrieval. Given a query, we want to retrieve data
items of the same class, and, in addition, rank these items according to intra-class similarity. In our training
data we assume partial knowledge: class labels are available, but the intra-class attributes are not. To compensate
for this knowledge gap we propose using an autoencoder, which can be trained to produce features
both with and without labels. Our main hypothesis is that network architectures that incorporate an autoencoder
can learn features that meaningfully cluster data based on the intra-class variability. We propose and
compare different architectures to construct our features, including a Siamese autoencoder (SAE), a classifying
autoencoder (CAE) and a separate classifier-autoencoder (SCA). We find that these architectures indeed
improve fine-grained retrieval compared to features trained purely in a supervised fashion for classification.
We perform e
xperiments on four datasets, and observe that the SCA generally outperforms the other two. In
particular, we obtain state of the art performance on fine-grained sketch retrieval.
(More)