Papers › Object Discovery from Motion-Guided Tokens

Object Discovery from Motion-Guided Tokens

27 Mar 2023CVPR 2023 1arXiv:2303.15555archive 2025-07-28

Zhipeng Bao, Pavel Tokmakov, Yu-Xiong Wang, Adrien Gaidon, Martial Hebert

Object discovery -- separating objects from the background without manual labels -- is a fundamental open challenge in computer vision. Previous methods struggle to go beyond clustering of low-level cues, whether handcrafted (e.g., color, texture) or learned (e.g., from auto-encoders). In this work, we augment the auto-encoder representation learning framework with two key components: motion-guidance and mid-level feature tokenization. Although both have been separately investigated, we introduce a new transformer decoder showing that their benefits can compound thanks to motion-guided vector quantization. We show that our architecture effectively leverages the synergy between motion and tokenization, improving upon the state of the art on both synthetic and real datasets. Our approach enables the emergence of interpretable object-specific mid-level features, demonstrating the benefits of motion-guidance (no labeling) and quantization (interpretability, memory efficiency).

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.

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

Code

Syntology 29 code samples: 28 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 29: 18 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 28 samples from 2 repositories, 17 ran (14 with no instrument failure; 3 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 18 samples that ran has no recorded date.

zpbao/discovery_obj_move officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
zpbao/motok officialmentioned in papermentioned on GitHubpytorchSyntology: 24 samples, 16 ran (3 instrument-failed) · 8 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

29 samples harvested: 18 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
14ran
11unverified

Licence: 29 of the 29 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 2 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. 1 sample is listed last, in a group without a repository. “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 5 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.

zpbao/discovery_obj_move official repository 4 samples, 1 ran (0 instrument-failed) · 3 unverified
Decoder in 210 papers models/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9bc24612fd19fd61 · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers models/model.py unverified no licence file found · pointer only · 3d5f91eee8334682 · report
SlotAttention in 11 papers models/model.py unverified no licence file found · pointer only · c91f2d386d8a0b9d · report
SlotAttentionAutoEncoder models/model.py unverified no licence file found · pointer only · 43591a6ff7ac7600 · report
zpbao/motok official repository 24 samples, 16 ran (3 instrument-failed) · 8 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · fcfd6a91cff8bff5 · report fixture: returned Attention · level recorded 2026-09-22
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7f064626e47dfce3 · report fixture: returned BasicBlock · level recorded 2026-09-22
Bottleneck in 98 papers models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1af3ad81514e01ab · report fixture: returned Bottleneck · level recorded 2026-09-22
FeedForward in 198 papers models/model.py ran · metamorphic tier: invariant no licence file found · pointer only · 209a0cdd69004ed6 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GEGLU in 20 papers
census: 12 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 594fabefbfea082e · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
PositionalEncoding in 126 papers
census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket
models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 86ce7d3fde6f587d · report fixture: returned PositionalEncoding · level recorded 2026-09-22
PreNorm in 34 papers models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · a6d3c1695434241b · report fixture: returned PreNorm · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 01574b6a1614b1a1 · report fixture: returned ResBlock · level recorded 2026-09-22
SoftPositionEmbed in 5 papers models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 45687c252db176ee · report fixture: returned SoftPositionEmbed · level recorded 2026-09-22
VQEmbedding models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · c69c1f11329402c9 · report fixture: returned VQEmbedding · level recorded 2026-09-22
VectorQuantization models/model.py ran no licence file found · pointer only · 52b032a9f378f705 · report fixture: returned VectorQuantization · level recorded 2026-09-22
VectorQuantizationStraightThrough models/model.py ran no licence file found · pointer only · 30c902aa572b0c90 · report fixture: returned VectorQuantizationStraightThrough · level recorded 2026-09-22
VectorQuantizedVAE models/model.py ran no licence file found · pointer only · fb9ea071c294e160 · report fixture: returned VectorQuantizedVAE · level recorded 2026-09-22
build_grid in 15 papers models/model.py ran · our draft was wrong no licence file found · pointer only · 8a1bbc075986fb5f · report fixture: signature resolution:list/1/int · returned Tensor · level recorded 2026-09-22
conv1x1 in 691 papers models/model.py ran · our draft was wrong no licence file found · pointer only · 18a2690463c2ec97 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers models/model.py ran · our draft was wrong no licence file found · pointer only · 3e8e29138f60555f · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-22
Encoder in 278 papers models/model.py unverified no licence file found · pointer only · dc3d45b68c59927d · report
PerceiverDecoder models/model.py unverified no licence file found · pointer only · c86e0d0d853fe4a1 · report
ResNet in 139 papers models/model.py unverified no licence file found · pointer only · 2e235c3f15a3bb8b · report
SlotAttention in 11 papers models/model.py unverified no licence file found · pointer only · 50957c73909eec68 · report
SlotAttentionAutoEncoder models/model.py unverified no licence file found · pointer only · bc3a09f53e252fc4 · report
_resnet in 27 papers models/model.py unverified no licence file found · pointer only · c4172180d85b140c · report
resnet18 in 432 papers models/model.py unverified no licence file found · pointer only · 3b2937dc40639bd1 · report
weights_init in 44 papers models/model.py unverified no licence file found · pointer only · 8f78954c8ba8c9d2 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
cache_fn in 13 papers repository not located ran · our draft was wrong licence of this copy not recorded · 8458f9ba0361ff43 · report fixture: signature f:callable/0/? · returned function · level recorded, date not recorded

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. 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. 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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for motion-guided vector quantization with a new transformer decoder (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for motion-guided vector quantization with a new transformer decoder (graph method: motion-guided vector quantization with a new transformer decoder). 27 bricks; individually on a fixture: 19 ran (of which 11 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 2 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. SlotAttentionAutoEncoder entry · level 0 · unverified · bc3a09f53e252fc4
  2. Encoder model · level 0 · unverified · dc3d45b68c59927d
  3. PerceiverDecoder helper · level 0 · unverified · c86e0d0d853fe4a1
  4. PositionalEncoding helper · level 1 · ran · 86ce7d3fde6f587d
  5. SlotAttention model · level 0 · unverified · 50957c73909eec68
  6. VectorQuantizedVAE helper · level 1 · ran · fb9ea071c294e160
  7. SoftPositionEmbed model · level 1 · ran · 45687c252db176ee
  8. resnet18 helper · level 0 · unverified · 3b2937dc40639bd1
  9. Attention helper · level 1 · ran · fcfd6a91cff8bff5
  10. FeedForward helper · level 1 · ran · 209a0cdd69004ed6
  11. PreNorm helper · level 1 · ran · a6d3c1695434241b
  12. cache_fn helper · level 1 · ran · our draft was wrong · 8458f9ba0361ff43
  13. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  14. ResBlock helper · level 1 · ran · 01574b6a1614b1a1
  15. VQEmbedding helper · level 1 · ran · c69c1f11329402c9
  16. weights_init helper · level 0 · unverified · 8f78954c8ba8c9d2
  17. build_grid helper · level 1 · ran · our draft was wrong · 8a1bbc075986fb5f
  18. BasicBlock helper · level 1 · ran · 7f064626e47dfce3
  19. ResNet helper · level 0 · unverified · 2e235c3f15a3bb8b
  20. _resnet helper · level 0 · unverified · c4172180d85b140c
  21. default helper · level 1 · ran · violated contract · 60fff7c3c400d7ff
  22. GEGLU helper · level 1 · ran · 594fabefbfea082e
  23. conv3x3 helper · level 1 · ran · our draft was wrong · 3e8e29138f60555f
  24. Bottleneck helper · level 1 · ran · 1af3ad81514e01ab
  25. conv1x1 helper · level 1 · ran · our draft was wrong · 18a2690463c2ec97
  26. VectorQuantization helper · level 1 · ran · 52b032a9f378f705
  27. VectorQuantizationStraightThrough helper · level 1 · ran · 30c902aa572b0c90

harvested Assembly for motion-guided vector quantization with a new transformer decoder (graph method: motion-guided vector quantization with a new transformer decoder). 13 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. SlotAttentionAutoEncoder entry · level 0 · unverified · 43591a6ff7ac7600
  2. Decoder model · level 1 · ran · 9bc24612fd19fd61
  3. Encoder model · level 0 · unverified · 3d5f91eee8334682
  4. SlotAttention model · level 0 · unverified · c91f2d386d8a0b9d
  5. SoftPositionEmbed helper · level 1 · ran · 45687c252db176ee
  6. resnet18 helper · level 0 · unverified · 3b2937dc40639bd1
  7. build_grid helper · level 1 · ran · our draft was wrong · 8a1bbc075986fb5f
  8. BasicBlock helper · level 1 · ran · 7f064626e47dfce3
  9. ResNet helper · level 0 · unverified · 2e235c3f15a3bb8b
  10. _resnet helper · level 0 · unverified · c4172180d85b140c
  11. conv3x3 helper · level 1 · ran · our draft was wrong · 3e8e29138f60555f
  12. Bottleneck helper · level 1 · ran · 1af3ad81514e01ab
  13. conv1x1 helper · level 1 · ran · our draft was wrong · 18a2690463c2ec97

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="2303.15555") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderObjectObject DiscoveryQuantizationRepresentation Learning

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