Object Segmentation Without Labels with Large-Scale Generative Models

Andrey Voynov, Stanislav Morozov, Artem Babenko
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10596-10606, 2021.

Abstract

The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing high-quality representations for transfer on downstream tasks. Furthermore, recent works also employed these representations in a fully unsupervised setup for image classification, reducing the need for human labels on the fine-tuning stage as well. This work demonstrates that large-scale unsupervised models can also perform a more challenging object segmentation task, requiring neither pixel-level nor image-level labeling. Namely, we show that recent unsupervised GANs allow to differentiate between foreground/background pixels, providing high-quality saliency masks. By extensive comparison on common benchmarks, we outperform existing unsupervised alternatives for object segmentation, achieving new state-of-the-art.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-voynov21a, title = {Object Segmentation Without Labels with Large-Scale Generative Models}, author = {Voynov, Andrey and Morozov, Stanislav and Babenko, Artem}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {10596--10606}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/voynov21a/voynov21a.pdf}, url = {https://proceedings.mlr.press/v139/voynov21a.html}, abstract = {The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing high-quality representations for transfer on downstream tasks. Furthermore, recent works also employed these representations in a fully unsupervised setup for image classification, reducing the need for human labels on the fine-tuning stage as well. This work demonstrates that large-scale unsupervised models can also perform a more challenging object segmentation task, requiring neither pixel-level nor image-level labeling. Namely, we show that recent unsupervised GANs allow to differentiate between foreground/background pixels, providing high-quality saliency masks. By extensive comparison on common benchmarks, we outperform existing unsupervised alternatives for object segmentation, achieving new state-of-the-art.} }
Endnote
%0 Conference Paper %T Object Segmentation Without Labels with Large-Scale Generative Models %A Andrey Voynov %A Stanislav Morozov %A Artem Babenko %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-voynov21a %I PMLR %P 10596--10606 %U https://proceedings.mlr.press/v139/voynov21a.html %V 139 %X The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing high-quality representations for transfer on downstream tasks. Furthermore, recent works also employed these representations in a fully unsupervised setup for image classification, reducing the need for human labels on the fine-tuning stage as well. This work demonstrates that large-scale unsupervised models can also perform a more challenging object segmentation task, requiring neither pixel-level nor image-level labeling. Namely, we show that recent unsupervised GANs allow to differentiate between foreground/background pixels, providing high-quality saliency masks. By extensive comparison on common benchmarks, we outperform existing unsupervised alternatives for object segmentation, achieving new state-of-the-art.
APA
Voynov, A., Morozov, S. & Babenko, A.. (2021). Object Segmentation Without Labels with Large-Scale Generative Models. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:10596-10606 Available from https://proceedings.mlr.press/v139/voynov21a.html.

Related Material