Unsupervised representation learning via information compression
Unsupervised representation learning via information compression
This paper explores a new paradigm for decomposing an image by seeking a compressed representation of the image through an information bottleneck. The compression is achieved iteratively by refining the reconstruction by adding patches that reduce the residual error. This is achieved by a network that is given the current residual errors and proposes bounding boxes that are down-sampled and passed to a variational auto-encoder (VAE). This acts as the bottleneck. The latent code is decoded by the VAE decoder and up-sampled to correct the reconstruction within the bounding box. The objective is to minimise the size of the latent codes of the VAE and the length of code needed to transmit the residual error. The iterations end when the size of the latent code exceeds the reduction in transmitting the residual error. We show that a very simple implementation is capable of finding meaningful bounding boxes and using those bounding boxes for downstream applications. We compare our model with other unsupervised object discovery models.
Information bottleneck, Object discovery, Unsupervised representation learning, VAE
567-578
Zeng, Zezhen
d340d998-568a-434f-95eb-ef39ee335912
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
2022
Zeng, Zezhen
d340d998-568a-434f-95eb-ef39ee335912
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Zeng, Zezhen, Hare, Jonathon and Prugel-Bennett, Adam
(2022)
Unsupervised representation learning via information compression.
El Yacoubi, Mounîm, Granger, Eric, Chi Yuen, Pong, Pal, Umapada and Vincent, Nicole
(eds.)
In Pattern Recognition and Artificial Intelligence : Third International Conference, ICPRAI 2022, Paris, France.
vol. 13363,
Springer.
.
(doi:10.1007/978-3-031-09037-0_46).
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper explores a new paradigm for decomposing an image by seeking a compressed representation of the image through an information bottleneck. The compression is achieved iteratively by refining the reconstruction by adding patches that reduce the residual error. This is achieved by a network that is given the current residual errors and proposes bounding boxes that are down-sampled and passed to a variational auto-encoder (VAE). This acts as the bottleneck. The latent code is decoded by the VAE decoder and up-sampled to correct the reconstruction within the bounding box. The objective is to minimise the size of the latent codes of the VAE and the length of code needed to transmit the residual error. The iterations end when the size of the latent code exceeds the reduction in transmitting the residual error. We show that a very simple implementation is capable of finding meaningful bounding boxes and using those bounding boxes for downstream applications. We compare our model with other unsupervised object discovery models.
Text
sub_33
- Accepted Manuscript
More information
e-pub ahead of print date: 2 June 2022
Published date: 2022
Additional Information:
Publisher Copyright:
© 2022, Springer Nature Switzerland AG.
Keywords:
Information bottleneck, Object discovery, Unsupervised representation learning, VAE
Identifiers
Local EPrints ID: 468261
URI: http://eprints.soton.ac.uk/id/eprint/468261
PURE UUID: 285dbfd7-f768-4f82-95e3-21359972c120
Catalogue record
Date deposited: 09 Aug 2022 16:37
Last modified: 06 Jun 2024 04:14
Export record
Altmetrics
Contributors
Author:
Zezhen Zeng
Author:
Jonathon Hare
Author:
Adam Prugel-Bennett
Editor:
Mounîm El Yacoubi
Editor:
Eric Granger
Editor:
Pong Chi Yuen
Editor:
Umapada Pal
Editor:
Nicole Vincent
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics