Unsupervised Attention-guided Image-to-Image Translation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of attention in human perception, we tackle this limitation by introducing unsupervised attention mechanisms that are jointly adversarially trained with the generators and discriminators. We demonstrate qualitatively and quantitatively that our approach attends to relevant regions in the image without requiring supervision, which creates more realistic mappings when compared to those of recent approaches.
LanguageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 31 (NIPS), 2018
EditorsS. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, R. Garnett
PublisherNeural Information Processing Systems Foundation, Inc.
Pages1-22
Number of pages22
StatusPublished - 3 Dec 2018
EventNIPS 2018 - 32nd Conference on Neural Information Processing Systems -
Duration: 3 Dec 20188 Dec 2018

Publication series

NameNIPS Proceedings
PublisherNeural Information Processing Systems Foundation, Inc.
ISSN (Electronic)1049-5258

Conference

ConferenceNIPS 2018 - 32nd Conference on Neural Information Processing Systems
Period3/12/188/12/18

Cite this

Alami Mejjati, Y., Richardt, C., Tompkin, J., Cosker, D., & Kim, K. I. (2018). Unsupervised Attention-guided Image-to-Image Translation. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 31 (NIPS), 2018 (pp. 1-22). (NIPS Proceedings). Neural Information Processing Systems Foundation, Inc..

Unsupervised Attention-guided Image-to-Image Translation. / Alami Mejjati, Youssef; Richardt, Christian; Tompkin, James; Cosker, Darren; Kim, Kwang In.

Advances in Neural Information Processing Systems 31 (NIPS), 2018. ed. / S. Bengio; H. Wallach; H. Larochelle; K. Grauman; N. Cesa-Bianchi; R. Garnett. Neural Information Processing Systems Foundation, Inc., 2018. p. 1-22 (NIPS Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alami Mejjati, Y, Richardt, C, Tompkin, J, Cosker, D & Kim, KI 2018, Unsupervised Attention-guided Image-to-Image Translation. in S Bengio, H Wallach, H Larochelle, K Grauman, N Cesa-Bianchi & R Garnett (eds), Advances in Neural Information Processing Systems 31 (NIPS), 2018. NIPS Proceedings, Neural Information Processing Systems Foundation, Inc., pp. 1-22, NIPS 2018 - 32nd Conference on Neural Information Processing Systems, 3/12/18.
Alami Mejjati Y, Richardt C, Tompkin J, Cosker D, Kim KI. Unsupervised Attention-guided Image-to-Image Translation. In Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, editors, Advances in Neural Information Processing Systems 31 (NIPS), 2018. Neural Information Processing Systems Foundation, Inc. 2018. p. 1-22. (NIPS Proceedings).
Alami Mejjati, Youssef ; Richardt, Christian ; Tompkin, James ; Cosker, Darren ; Kim, Kwang In. / Unsupervised Attention-guided Image-to-Image Translation. Advances in Neural Information Processing Systems 31 (NIPS), 2018. editor / S. Bengio ; H. Wallach ; H. Larochelle ; K. Grauman ; N. Cesa-Bianchi ; R. Garnett. Neural Information Processing Systems Foundation, Inc., 2018. pp. 1-22 (NIPS Proceedings).
@inproceedings{4a4207647a1f402c8e428b7e21de2958,
title = "Unsupervised Attention-guided Image-to-Image Translation",
abstract = "Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of attention in human perception, we tackle this limitation by introducing unsupervised attention mechanisms that are jointly adversarially trained with the generators and discriminators. We demonstrate qualitatively and quantitatively that our approach attends to relevant regions in the image without requiring supervision, which creates more realistic mappings when compared to those of recent approaches.",
author = "{Alami Mejjati}, Youssef and Christian Richardt and James Tompkin and Darren Cosker and Kim, {Kwang In}",
year = "2018",
month = "12",
day = "3",
language = "English",
series = "NIPS Proceedings",
publisher = "Neural Information Processing Systems Foundation, Inc.",
pages = "1--22",
editor = "S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett",
booktitle = "Advances in Neural Information Processing Systems 31 (NIPS), 2018",

}

TY - GEN

T1 - Unsupervised Attention-guided Image-to-Image Translation

AU - Alami Mejjati, Youssef

AU - Richardt, Christian

AU - Tompkin, James

AU - Cosker, Darren

AU - Kim, Kwang In

PY - 2018/12/3

Y1 - 2018/12/3

N2 - Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of attention in human perception, we tackle this limitation by introducing unsupervised attention mechanisms that are jointly adversarially trained with the generators and discriminators. We demonstrate qualitatively and quantitatively that our approach attends to relevant regions in the image without requiring supervision, which creates more realistic mappings when compared to those of recent approaches.

AB - Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of attention in human perception, we tackle this limitation by introducing unsupervised attention mechanisms that are jointly adversarially trained with the generators and discriminators. We demonstrate qualitatively and quantitatively that our approach attends to relevant regions in the image without requiring supervision, which creates more realistic mappings when compared to those of recent approaches.

M3 - Conference contribution

T3 - NIPS Proceedings

SP - 1

EP - 22

BT - Advances in Neural Information Processing Systems 31 (NIPS), 2018

A2 - Bengio, S.

A2 - Wallach, H.

A2 - Larochelle, H.

A2 - Grauman, K.

A2 - Cesa-Bianchi, N.

A2 - Garnett, R.

PB - Neural Information Processing Systems Foundation, Inc.

ER -