Worrall, DE;
Garbin, SJ;
Turmukhambetov, D;
Brostow, GJ;
(2017)
Interpretable transformations with Encoder-Decoder Networks.
In:
Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV).
(pp. pp. 5737-5746).
IEEE: Venice, Italy.
Preview |
Text
Worrall_Interpretable_Transformations_With_ICCV_2017_paper[1].pdf - Published Version Download (1MB) | Preview |
Abstract
Deep feature spaces have the capacity to encode complex transformations of their input data. However, understanding the relative feature-space relationship between two transformed encoded images is difficult. For instance, what is the relative feature space relationship between two rotated images? What is decoded when we interpolate in feature space? Ideally, we want to disentangle confounding factors, such as pose, appearance, and illumination, from object identity. Disentangling these is difficult because they interact in very nonlinear ways. We propose a simple method to construct a deep feature space, with explicitly disentangled representations of several known transformations. A person or algorithm can then manipulate the disentangled representation, for example, to re-render an image with explicit control over parameterized degrees of freedom. The feature space is constructed using a transforming encoder-decoder network with a custom feature transform layer, acting on the hidden representations. We demonstrate the advantages of explicit disentangling on a variety of datasets and transformations, and as an aid for traditional tasks, such as classification.
| Type: | Proceedings paper |
|---|---|
| Title: | Interpretable transformations with Encoder-Decoder Networks |
| Event: | 2017 IEEE International Conference on Computer Vision (ICCV) |
| Location: | Venice, Italy |
| Dates: | 22 October 2017 - 29 October 2017 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ICCV.2017.611 |
| Publisher version: | https://doi.org/10.1109/ICCV.2017.611 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Three-dimensional displays, Two dimensional displays, Aerospace electronics, Feature extraction, Transforms, Training |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10039218 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
