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 PDFCodeMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

Syntology holds a reference implementation of GENESIS-V2, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='GENESIS-V2') (how to connect); the free check have('2104.09958') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

applied-ai-lab/genesis officialmentioned in papermentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
jinyangyuan/genesis mentioned on GitHubpytorchGPL-3.0Syntology: not harvested 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.

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

1 assembly on this paper: 0 harvested, 1 generated.

generated Assembly for GENESIS-V2 (graph method: GENESIS-V2), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. distance_kernel entry · level 3 · ran; the contract check could not run · 7481591022ec5bfe22dc87c9eae0705b88416a199b5e7863064f3878186cc69e

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2104.09958") returns these assemblies with each brick's role and wiring (how to connect).

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