Papers › Object-Centric Learning with Slot Attention

Object-Centric Learning with Slot Attention

26 Jun 2020NeurIPS 2020 12arXiv:2006.15055archive 2025-07-28

Francesco Locatello, Dirk Weissenborn, Thomas Unterthiner, Aravindh Mahendran, Georg Heigold, Jakob Uszkoreit, Alexey Dosovitskiy, Thomas Kipf

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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 Slot Attention, 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). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Slot Attention') (how to connect); the free check have('2006.15055') needs no token.

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

Code

Syntology 21 code samples harvested from 7 repositories linked to this paper: 14 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 20 samples from 6 repositories, 14 ran (9 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 14 samples that ran has no recorded date.

google-research/google-research officialtfSyntology: 1 sample, 0 ran · 1 unverified report
HHousen/object-discovery-pytorch mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 unverified report
a-imamshah/savi-pytorch mentioned on GitHubpytorchSyntology: 7 samples, 5 ran (1 instrument-failed) · 2 unverified report
a-imamshah/slotattention.jl mentioned on GitHubtfSyntology: not harvested report
adityabingi/Slot-Attention mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lucidrains/slot-attention mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (2 instrument-failed) · 2 unverified report
untitled-ai/slot_attention mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Michedev/slot-attention-pytorch pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

21 samples harvested: 14 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
8ran
7unverified

Licence: 7 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

google-research/google-research official repository 1 sample, 0 ran · 1 unverified
SlotAttention in 11 papers slot_attention/model.py unverified Apache-2.0 (permissive) · d27f9166117666a4 · report
HHousen/object-discovery-pytorch community (archive-listed) 4 samples, 3 ran (2 instrument-failed) · 1 unverified
SlotAttention in 11 papers object_discovery/slot_attention_model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2866aea2f2e12f24 · report fixture: returned SlotAttention · level recorded 2026-09-22
gru_cell object_discovery/slot_attention_model.py ran · our draft was wrong Apache-2.0 (permissive) · 4d2babbfd7692155 · report fixture: signature input_size:int/0/int, hidden_size:int/0/int, bias:bool/0/bool · returned GRUCell · level recorded 2026-09-22
linear in 88 papers object_discovery/slot_attention_model.py ran · our draft was wrong Apache-2.0 (permissive) · e6a98db4b3460c98 · report fixture: signature in_features:int/0/int, out_features:int/0/int, bias:bool/0/bool, weight_init:str/0/str, gain:float/0/float · returned Linear · level recorded 2026-09-22
assert_shape object_discovery/slot_attention_model.py unverified Apache-2.0 (permissive) · 79554477c54457b2 · report
a-imamshah/savi-pytorch community (archive-listed) 7 samples, 5 ran (1 instrument-failed) · 2 unverified
Corrector in 5 papers model.py ran no licence file found · pointer only · e1aebfe322a32f90 · report fixture: returned Corrector · level recorded 2026-09-22
SAViParams model.py ran no licence file found · pointer only · 36ddba1f54930ede · report fixture: returned SAViParams · level recorded 2026-09-22
SoftPositionEmbed in 5 papers model.py ran no licence file found · pointer only · b63e60d7d9b40cf2 · report fixture: returned SoftPositionEmbed · level recorded 2026-09-22
build_grid in 15 papers model.py ran · our draft was wrong no licence file found · pointer only · dc25809a5c10c08d · report fixture: signature resolution:list/1/int · returned Tensor · level recorded 2026-09-22
conv_transpose_out_shape model.py ran · honoured contract fingerprinted no licence file found · pointer only · a841bb8d8f1cb615 · report fixture: signature in_size:int/0/int, stride:int/0/int, padding:int/0/int, kernel_size:int/0/int, out_padding:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
SAViModel model.py unverified no licence file found · pointer only · fc3484e23be41e9a · report
assert_shape model.py unverified no licence file found · pointer only · 85fd1318e1fa8108 · report
adityabingi/Slot-Attention community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SlotAttention in 11 papers model.py ran · metamorphic tier: invariant MIT (permissive) · 423454f6dee02cea · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
lucidrains/slot-attention community (archive-listed) 5 samples, 3 ran (2 instrument-failed) · 2 unverified
SlotAttention in 11 papers slot_attention/slot_attention.py ran · metamorphic tier: deterministic MIT (permissive) · 8a880cb0b42760d3 · report fixture: returned SlotAttention · level recorded 2026-09-22
l1norm in 14 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
slot_attention/slot_attention.py ran · our draft was wrong fingerprinted MIT (permissive) · fdf3401cb2b8d73a · report fixture: signature t:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded, date not recorded
l1norm in 14 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
slot_attention/slot_attention.py ran · our draft was wrong fingerprinted MIT (permissive) · f3e9841706a261f0 · report fixture: signature t:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
default in 430 papers slot_attention/slot_attention.py unverified MIT (permissive) · 1c5befd817fba622 · report
untitled-ai/slot_attention community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
SlotAttention in 11 papers slot_attention/model.py ran Apache-2.0 (permissive) · 6976478c1fa514f0 · report fixture: returned SlotAttention · level recorded 2026-09-22
assert_shape slot_attention/model.py unverified Apache-2.0 (permissive) · b59864b89b5b89e0 · report
Michedev/slot-attention-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SlotAttentionModule slot_attention_pytorch/slot_attention_module.py ran MIT (permissive) · 4032cffa99401bb9 · report fixture: returned SlotAttentionModule · level recorded 2026-09-22

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. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. 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". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. 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.

8 assemblies on this paper: 7 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for Slot Attention (graph method: Slot Attention), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

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

  1. slot_attention_weighted_mean entry · level 3 · ran · honoured contract · 794fac4aca0830f9993d6b4ba352d89406fdac07d279eeb4f0beeb773b77ebbd

7 sibling assemblies for Slot Attention (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Slot Attention (graph method: Slot Attention). 4 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. SlotAttention entry · level 1 · ran · 8a880cb0b42760d3
  2. default helper · level 1 · ran · violated contract · 99b3563ebc6734ad
  3. l1norm helper · level 1 · ran · our draft was wrong · f3e9841706a261f0
  4. exists helper · level 1 · ran · violated contract · b7c3487f192e31b7

harvested Assembly for Slot Attention (graph method: Slot Attention). 4 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. SlotAttention entry · level 1 · ran · 2866aea2f2e12f24
  2. assert_shape helper · level 0 · unverified · 79554477c54457b2
  3. gru_cell helper · level 1 · ran · our draft was wrong · 4d2babbfd7692155
  4. linear helper · level 1 · ran · our draft was wrong · e6a98db4b3460c98

harvested Assembly for Slot Attention (graph method: Slot Attention). 7 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. SAViModel entry · level 0 · unverified · fc3484e23be41e9a
  2. Corrector model · level 1 · ran · e1aebfe322a32f90
  3. SoftPositionEmbed model · level 1 · ran · b63e60d7d9b40cf2
  4. assert_shape helper · level 0 · unverified · 85fd1318e1fa8108
  5. conv_transpose_out_shape helper · level 1 · ran · honoured contract · a841bb8d8f1cb615
  6. build_grid helper · level 1 · ran · our draft was wrong · dc25809a5c10c08d
  7. SAViParams helper · level 1 · ran · 36ddba1f54930ede

harvested Assembly for Slot Attention (graph method: Slot Attention). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. SlotAttentionModule entry · level 1 · ran · 4032cffa99401bb9

harvested Assembly for Slot Attention (graph method: Slot Attention). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. SlotAttention entry · level 1 · ran · 6976478c1fa514f0
  2. assert_shape helper · level 0 · unverified · b59864b89b5b89e0

harvested Assembly for Slot Attention (graph method: Slot Attention). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. SlotAttention entry · level 0 · unverified · d27f9166117666a4

harvested Assembly for Slot Attention (graph method: Slot Attention). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. SlotAttention entry · level 1 · ran · 423454f6dee02cea

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="2006.15055") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ObjectObject DiscoveryProperty Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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