Papers › Memory-guided Unsupervised Image-to-image Translation

Memory-guided Unsupervised Image-to-image Translation

12 Apr 2021CVPR 2021 1arXiv:2104.05170archive 2025-07-28

Somi Jeong, Youngjung Kim, Eungbean Lee, Kwanghoon Sohn

We present a novel unsupervised framework for instance-level image-to-image translation. Although recent advances have been made by incorporating additional object annotations, existing methods often fail to handle images with multiple disparate objects. The main cause is that, during inference, they apply a global style to the whole image and do not consider the large style discrepancy between instance and background, or within instances. To address this problem, we propose a class-aware memory network that explicitly reasons about local style variations. A key-values memory structure, with a set of read/update operations, is introduced to record class-wise style variations and access them without requiring an object detector at the test time. The key stores a domain-agnostic content representation for allocating memory items, while the values encode domain-specific style representations. We also present a feature contrastive loss to boost the discriminative power of memory items. We show that by incorporating our memory, we can transfer class-aware and accurate style representations across domains. Experimental results demonstrate that our model outperforms recent instance-level methods and achieves state-of-the-art performance.

PaperPDFConference PDFCode 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 25 code samples harvested from 1 repository linked to this paper: 20 ran (of which 14 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 25 samples from 1 repository, 20 ran (14 with no instrument failure; 6 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.

HsinYingLee/DRIT found in paper text by SyntologySyntology: 25 samples, 20 ran (6 instrument-failed) · 5 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

25 samples harvested: 20 ran (of which 14 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 5 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.

6ran · our draft was wrong
14ran
5unverified

Licence: 25 of the 25 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 HsinYingLee/DRIT. “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 7 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.

HsinYingLee/DRIT found in paper text by Syntology 25 samples, 20 ran (6 instrument-failed) · 5 unverified
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f8aba562a629bcc2 · report fixture: returned BasicBlock · level recorded 2026-09-22
Dis src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 740cc4c112a7292f · report fixture: returned Dis · level recorded 2026-09-22
Dis_content src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · c03766f07a3fc8ae · report fixture: returned Dis_content · level recorded 2026-09-22
E_attr src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · ff99bd28542eb0b7 · report fixture: returned E_attr · level recorded 2026-09-22
E_attr_concat src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 51b77b83aa8057da · report fixture: returned E_attr_concat · level recorded 2026-09-22
G in 6 papers src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8555d745df56cef9 · report fixture: returned G · level recorded 2026-09-22
GaussianNoiseLayer src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b3f1716e12bfd7ac · report fixture: returned GaussianNoiseLayer · level recorded 2026-09-22
INSResBlock src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 760216b6617fdf18 · report fixture: returned INSResBlock · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 62b928ee0474739e · report fixture: returned LayerNorm · level recorded 2026-09-22
LeakyReLUConv2d src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9010126e54b1ee4e · report fixture: returned LeakyReLUConv2d · level recorded 2026-09-22
MisINSResBlock src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 13c89236de773a2e · report fixture: returned MisINSResBlock · level recorded 2026-09-22
ReLUINSConv2d src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f438c4b487df22da · report fixture: returned ReLUINSConv2d · level recorded 2026-09-22
ReLUINSConvTranspose2d src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · dc83bd8478c21ca9 · report fixture: returned ReLUINSConvTranspose2d · level recorded 2026-09-22
SpectralNorm in 9 papers src/model.py ran no licence file found · pointer only · 43fb0d94c6f43e76 · report fixture: returned SpectralNorm · level recorded 2026-09-22
conv3x3 in 1,376 papers src/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c8b7ae4531a13031 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned list · level recorded 2026-09-22
convMeanpool src/model.py ran · our draft was wrong no licence file found · pointer only · ac9996943f2e1621 · report fixture: signature inplanes:int/0/int, outplanes:int/0/int · returned Sequential · level recorded 2026-09-22
get_non_linearity src/model.py ran · our draft was wrong no licence file found · pointer only · bc9778c1df0b2c6c · report fixture: signature layer_type:str/0/str · returned partial · level recorded 2026-09-22
get_scheduler in 122 papers src/model.py ran · our draft was wrong no licence file found · pointer only · fcd2cbd6dab69214 · report fixture: signature optimizer:Adam/0/?, opts:Options/0/?, cur_ep:int/0/int · returned LambdaLR · level recorded 2026-09-22
meanpoolConv src/model.py ran · our draft was wrong no licence file found · pointer only · 623150b77cda933f · report fixture: signature inplanes:int/0/int, outplanes:int/0/int · returned Sequential · level recorded 2026-09-22
spectral_norm in 42 papers src/model.py ran · our draft was wrong no licence file found · pointer only · 8de6eeebb8e3638f · report fixture: signature module:callable/0/?, name:str/0/str, n_power_iterations:int/0/int, eps:float/0/float, dim:NoneType/0/? · returned Linear · level recorded 2026-09-22
DRIT src/model.py unverified no licence file found · pointer only · 35c8e32f50daf88d · report
E_content src/model.py unverified no licence file found · pointer only · 4441b221040411ce · report
G_concat src/model.py unverified no licence file found · pointer only · 11297da98dec3c4c · report
MultiScaleDis src/model.py unverified no licence file found · pointer only · 424e28d74856b61a · report
gaussian_weights_init src/model.py unverified no licence file found · pointer only · ecaec8fbc5fc577d · report

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.

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

harvested Assembly for memory-guided unsupervised image-to-image translation (graph method: memory-guided unsupervised image-to-image translation). 25 bricks; individually on a fixture: 20 ran (of which 14 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. DRIT entry · level 0 · unverified · 35c8e32f50daf88d
  2. Dis helper · level 1 · ran · 740cc4c112a7292f
  3. Dis_content model · level 1 · ran · c03766f07a3fc8ae
  4. E_attr model · level 1 · ran · ff99bd28542eb0b7
  5. E_attr_concat helper · level 1 · ran · 51b77b83aa8057da
  6. E_content model · level 0 · unverified · 4441b221040411ce
  7. G model · level 1 · ran · 8555d745df56cef9
  8. G_concat helper · level 0 · unverified · 11297da98dec3c4c
  9. MultiScaleDis model · level 0 · unverified · 424e28d74856b61a
  10. gaussian_weights_init helper · level 0 · unverified · ecaec8fbc5fc577d
  11. get_non_linearity helper · level 1 · ran · our draft was wrong · bc9778c1df0b2c6c
  12. get_scheduler scheduler · level 1 · ran · our draft was wrong · fcd2cbd6dab69214
  13. LeakyReLUConv2d helper · level 1 · ran · 9010126e54b1ee4e
  14. spectral_norm helper · level 1 · ran · our draft was wrong · 8de6eeebb8e3638f
  15. BasicBlock helper · level 1 · ran · f8aba562a629bcc2
  16. GaussianNoiseLayer helper · level 1 · ran · b3f1716e12bfd7ac
  17. INSResBlock helper · level 1 · ran · 760216b6617fdf18
  18. ReLUINSConv2d helper · level 1 · ran · f438c4b487df22da
  19. MisINSResBlock helper · level 1 · ran · 13c89236de773a2e
  20. ReLUINSConvTranspose2d helper · level 1 · ran · dc83bd8478c21ca9
  21. SpectralNorm helper · level 1 · ran · 43fb0d94c6f43e76
  22. conv3x3 helper · level 1 · ran · our draft was wrong · c8b7ae4531a13031
  23. convMeanpool helper · level 1 · ran · our draft was wrong · ac9996943f2e1621
  24. meanpoolConv helper · level 1 · ran · our draft was wrong · 623150b77cda933f
  25. LayerNorm helper · level 1 · ran · 62b928ee0474739e

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="2104.05170") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image-to-Image TranslationTranslationUnsupervised Image-To-Image Translation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Memory Network

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