Papers › Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for...

Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption

7 Sep 2023ICCV 2023 1arXiv:2309.03729archive 2025-07-28

Teng Hu, Jiangning Zhang, Liang Liu, Ran Yi, Siqi Kou, Haokun Zhu, Xu Chen, Yabiao Wang, Chengjie Wang, Lizhuang Ma

Training a generative model with limited number of samples is a challenging task. Current methods primarily rely on few-shot model adaption to train the network. However, in scenarios where data is extremely limited (less than 10), the generative network tends to overfit and suffers from content degradation. To address these problems, we propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss, which targets different learning objectives at distinct training stages of the diffusion model. Specifically, we design a phasic training strategy with phasic content fusion to help our model learn content and style information when t is large, and learn local details of target domain when t is small, leading to an improvement in the capture of content, style and local details. Furthermore, we introduce a novel directional distribution consistency loss that ensures the consistency between the generated and source distributions more efficiently and stably than the prior methods, preventing our model from overfitting. Finally, we propose a cross-domain structure guidance strategy that enhances structure consistency during domain adaptation. Theoretical analysis, qualitative and quantitative experiments demonstrate the superiority of our approach in few-shot generative model adaption tasks compared to state-of-the-art methods. The source code is available at: https://github.com/sjtuplayer/few-shot-diffusion.

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 25 code samples harvested from 1 repository linked to this paper: 15 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 15 ran (13 with no instrument failure; 2 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sjtuplayer/few-shot-diffusion officialmentioned in papermentioned on GitHubpytorchSyntology: 25 samples, 15 ran (2 instrument-failed) · 10 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: 15 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 10 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.

2ran · our draft was wrong
13ran
10unverified

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 sjtuplayer/few-shot-diffusion. “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 8 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.

sjtuplayer/few-shot-diffusion official repository 25 samples, 15 ran (2 instrument-failed) · 10 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
model/big_unet.py ran no licence file found · pointer only · d16665e1f56437fb · report fixture: signature x:Tensor/4/float, scale_shift:tuple/1/Tensor · returned Tensor · level recorded 2026-09-24
CheckpointFunction in 6 papers model/big_unet.py ran no licence file found · pointer only · 27faeacc0d8cf344 · report fixture: returned CheckpointFunction · level recorded 2026-09-22
Downsample in 58 papers model/big_unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 8c5676227adb2492 · report fixture: returned Downsample · 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
model/big_unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f5fbdad1df60c363 · report fixture: returned LayerNorm · level recorded 2026-09-22
LinearAttention in 20 papers model/big_unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · c71125f439d1d5ea · report fixture: returned LinearAttention · level recorded 2026-09-22
PreNorm in 34 papers model/big_unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5b3345b4a26536a9 · report fixture: returned PreNorm · level recorded 2026-09-22
QKVAttention in 25 papers model/big_unet.py ran no licence file found · pointer only · 5ebe00ac9e392f07 · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
QKVAttentionLegacy in 20 papers model/big_unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · c21412aa89ed28a7 · report fixture: returned QKVAttentionLegacy · level recorded 2026-09-22
Residual in 24 papers model/big_unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d2f3f77a4605ff1f · report fixture: returned Residual · level recorded 2026-09-22
ResnetBlock in 49 papers model/big_unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9cc672082b6782fb · report fixture: returned ResnetBlock · level recorded 2026-09-22
SinusoidalPosEmb in 18 papers
census: 6 implementations from 6 papers, 3 distinct outputs on one shared input
model/big_unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 7b3d0ed0839661d7 · report fixture: returned SinusoidalPosEmb · level recorded 2026-09-22
Upsample in 77 papers model/big_unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6998a3677700ee6c · report fixture: returned Upsample · level recorded 2026-09-22
WeightStandardizedConv2d model/big_unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 179fd1dd12f18912 · report fixture: returned WeightStandardizedConv2d · level recorded 2026-09-22
normalization in 70 papers
census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
model/big_unet.py ran · our draft was wrong no licence file found · pointer only · 5b31715a9b105926 · report fixture: signature channels:int/0/int · returned GroupNorm32 · level recorded 2026-09-22
timestep_embedding in 79 papers
census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float32
model/big_unet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b0aa348a2f95ef0f · report fixture: signature timesteps:Tensor/1/float, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded 2026-09-22
AttentionBlock in 69 papers model/big_unet.py unverified no licence file found · pointer only · 33dbefd057c8df79 · report
MyUnet model/big_unet.py unverified no licence file found · pointer only · 79d0a98cc75ac0c8 · report
TimestepBlock in 11 papers model/big_unet.py unverified no licence file found · pointer only · 40fb9bc947892adc · report
TimestepEmbedSequential in 28 papers model/big_unet.py unverified no licence file found · pointer only · ed74c5af0b1d1d51 · report
checkpoint in 42 papers model/big_unet.py unverified no licence file found · pointer only · fb150e1f7e53041e · report
convert_module_to_f16 model/big_unet.py unverified no licence file found · pointer only · ac07425399caf784 · report
convert_module_to_f32 model/big_unet.py unverified no licence file found · pointer only · b283a8ab305dc007 · report
count_flops_attn model/big_unet.py unverified no licence file found · pointer only · 0c49097ae6ff37ef · report
style_condtioner model/big_unet.py unverified no licence file found · pointer only · 176cae28c26d5cf2 · 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 Phasic Content Fusing Diffusion Model (graph method: Phasic Content Fusing Diffusion Model). 31 bricks; individually on a fixture: 19 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. MyUnet entry · level 0 · unverified · 79d0a98cc75ac0c8
  2. AttentionBlock model · level 0 · unverified · 33dbefd057c8df79
  3. Downsample model · level 1 · ran · 8c5676227adb2492
  4. LinearAttention helper · level 1 · ran · c71125f439d1d5ea
  5. PreNorm helper · level 1 · ran · 5b3345b4a26536a9
  6. ResBlock model · level 0 · unverified · 0fc14114982f5c9d
  7. Residual helper · level 1 · ran · d2f3f77a4605ff1f
  8. ResnetBlock helper · level 1 · ran · 9cc672082b6782fb
  9. SinusoidalPosEmb helper · level 1 · ran · 7b3d0ed0839661d7
  10. TimestepEmbedSequential model · level 0 · unverified · ed74c5af0b1d1d51
  11. Upsample model · level 1 · ran · 6998a3677700ee6c
  12. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  13. convert_module_to_f16 helper · level 0 · unverified · ac07425399caf784
  14. convert_module_to_f32 helper · level 0 · unverified · b283a8ab305dc007
  15. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  16. normalization helper · level 1 · ran · our draft was wrong · 5b31715a9b105926
  17. style_condtioner helper · level 0 · unverified · 176cae28c26d5cf2
  18. timestep_embedding helper · level 1 · ran · our draft was wrong · b0aa348a2f95ef0f
  19. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  20. QKVAttention helper · level 1 · ran · 5ebe00ac9e392f07
  21. QKVAttentionLegacy helper · level 1 · ran · c21412aa89ed28a7
  22. checkpoint helper · level 0 · unverified · fb150e1f7e53041e
  23. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae
  24. LayerNorm helper · level 1 · ran · f5fbdad1df60c363
  25. TimestepBlock helper · level 0 · unverified · 40fb9bc947892adc
  26. Block helper · level 1 · ran · d16665e1f56437fb
  27. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  28. GroupNorm32 helper · level 1 · ran · 426c2385fa431d9a
  29. count_flops_attn helper · level 0 · unverified · 0c49097ae6ff37ef
  30. CheckpointFunction helper · level 1 · ran · 27faeacc0d8cf344
  31. WeightStandardizedConv2d helper · level 1 · ran · 179fd1dd12f18912

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="2309.03729") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Domain Adaptationmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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