Papers › Object Segmentation Without Labels with Large-Scale Generative Models

Object Segmentation Without Labels with Large-Scale Generative Models

8 Jun 2020arXiv:2006.04988archive 2025-07-28

Andrey Voynov, Stanislav Morozov, Artem Babenko

The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks. Furthermore, recent works 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 standard benchmarks, we outperform existing unsupervised alternatives for object segmentation, achieving new state-of-the-art.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

anvoynov/BigGANsAreWatching officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationObjectSaliency DetectionSegmentationSelf-Supervised LearningSemantic SegmentationUnsupervised Object Segmentationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAdamAverage PoolingBatch NormalizationBigBiGANBigGANCReLUConditional Batch NormalizationConvolutionDense ConnectionsEarly StoppingFeedforward NetworkGAN Hinge LossGlobal Average PoolingLinear LayerNon-Local BlockNon-Local OperationOff-Diagonal Orthogonal RegularizationPointwise ConvolutionProjection DiscriminatorReLUResidual BlockResidual ConnectionRevNetReversible Residual BlockSAGANSoftmaxSpectral NormalizationTTURTruncation Trick

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections