Papers › GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

20 Apr 2021NeurIPS 2021 12arXiv:2104.09958archive 2025-07-28

Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

Advances in unsupervised learning of object-representations have culminated in the development of a broad range of methods for unsupervised object segmentation and interpretable object-centric scene generation. These methods, however, are limited to simulated and real-world datasets with limited visual complexity. Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations. In contrast to established paradigms, this work proposes an embedding-based approach in which embeddings of pixels are clustered in a differentiable fashion using a stochastic stick-breaking process. Similar to iterative refinement, this clustering procedure also leads to randomly ordered object representations, but without the need of initialising a fixed number of clusters a priori. This is used to develop a new model, GENESIS-v2, which can infer a variable number of object representations without using RNNs or iterative refinement. We show that GENESIS-v2 performs strongly in comparison to recent baselines in terms of unsupervised image segmentation and object-centric scene generation on established synthetic datasets as well as more complex real-world datasets.

PaperPDFConference PDFCode

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

Code

applied-ai-lab/genesis officialmentioned in papermentioned on GitHubpytorchGPL-3.0 report
jinyangyuan/genesis mentioned on GitHubpytorchGPL-3.0 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

ClusteringImage GenerationImage SegmentationObjectRepresentation LearningScene GenerationUnsupervised Image SegmentationUnsupervised Object Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ObjectsRoom GENESIS-V2 FID 52.6 #1 of 3 Archive leaderboard report
Image Generation ObjectsRoom GENESIS FID 62.8 #2 of 3 Archive leaderboard report
Image Generation ObjectsRoom MONET-G FID 205.7 #3 of 3 Archive leaderboard report
Image Generation ShapeStacks GENESIS-V2 FID 112.7 #1 of 3 Archive leaderboard report
Image Generation ShapeStacks GENESIS FID 186.8 #2 of 3 Archive leaderboard report
Image Generation ShapeStacks MONET-G FID 197.8 #3 of 3 Archive leaderboard report
Unsupervised Object Segmentation ObjectsRoom GENESIS-V2 ARI-FG 0.84 #2 of 5 Archive leaderboard report
Unsupervised Object Segmentation ObjectsRoom SlotAttention ARI-FG 0.79 #3 of 5 Archive leaderboard report
Unsupervised Object Segmentation ObjectsRoom GENESIS ARI-FG 0.63 #4 of 5 Archive leaderboard report
Unsupervised Object Segmentation ObjectsRoom MONET-G ARI-FG 0.54 #5 of 5 Archive leaderboard report
Unsupervised Object Segmentation ShapeStacks GENESIS-V2 ARI-FG 0.81 #2 of 5 Archive leaderboard report
Unsupervised Object Segmentation ShapeStacks SlotAttention ARI-FG 0.76 #3 of 5 Archive leaderboard report
Unsupervised Object Segmentation ShapeStacks GENESIS ARI-FG 0.70 #4 of 5 Archive leaderboard report
Unsupervised Object Segmentation ShapeStacks MONET-G ARI-FG 0.70 #5 of 5 Archive leaderboard report
Unsupervised Object Segmentation Shelf&Tote Training Dataset GENESIS-V2 ARI 0.55 #1 of 4 Archive leaderboard report
Unsupervised Object Segmentation Shelf&Tote Training Dataset MONET-G ARI 0.11 #2 of 4 Archive leaderboard report
Unsupervised Object Segmentation Shelf&Tote Training Dataset GENESIS ARI 0.04 #3 of 4 Archive leaderboard report
Unsupervised Object Segmentation Shelf&Tote Training Dataset SlotAttention ARI 0.03 #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: IC-SBP

AdamConcatenated Skip ConnectionConvolutionGECOGroup NormalizationIC-SBPLSTMMax PoolingReLUSigmoid ActivationTanh ActivationTransposed convolutionU-Net

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