Fine-Grained Retrieval with Autoencoders

Portenier, Tiziano; Hu, Qiyang; Favaro, Paolo; Zwicker, Matthias (January 2018). Fine-Grained Retrieval with Autoencoders. In: 13th International Conference on Computer Vision Theory and Applications. Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018): Vol. 5 (pp. 85-95). SCITEPRESS 10.5220/0006602100850095

[img] Text
2a54d015c8fb0733a2717cfbe0b83d8f0dd3.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (8MB) | Request a copy

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 experiments 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.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

08 Faculty of Science > Institute of Computer Science (INF)

UniBE Contributor:

Portenier, Tiziano; Hu, Qiyang; Favaro, Paolo and Zwicker, Matthias

Subjects:

000 Computer science, knowledge & systems
500 Science > 510 Mathematics

ISBN:

978-989-758-290-5

Series:

Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018)

Publisher:

SCITEPRESS

Language:

English

Submitter:

Xiaochen Wang

Date Deposited:

28 May 2019 15:56

Last Modified:

28 Oct 2019 22:00

Publisher DOI:

10.5220/0006602100850095

BORIS DOI:

10.7892/boris.126529

URI:

https://boris.unibe.ch/id/eprint/126529

Actions (login required)

Edit item Edit item
Provide Feedback