Papers › Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

15 Apr 2023CVPR 2023 1arXiv:2304.07574archive 2025-07-28

Yunqing Zhao, Chao Du, Milad Abdollahzadeh, Tianyu Pang, Min Lin, Shuicheng Yan, Ngai-Man Cheung

Few-shot image generation (FSIG) learns to generate diverse and high-fidelity images from a target domain using a few (e.g., 10) reference samples. Existing FSIG methods select, preserve and transfer prior knowledge from a source generator (pretrained on a related domain) to learn the target generator. In this work, we investigate an underexplored issue in FSIG, dubbed as incompatible knowledge transfer, which would significantly degrade the realisticness of synthetic samples. Empirical observations show that the issue stems from the least significant filters from the source generator. To this end, we propose knowledge truncation to mitigate this issue in FSIG, which is a complementary operation to knowledge preservation and is implemented by a lightweight pruning-based method. Extensive experiments show that knowledge truncation is simple and effective, consistently achieving state-of-the-art performance, including challenging setups where the source and target domains are more distant. Project Page: yunqing-me.github.io/RICK.

PaperPDFConference PDFCodeCode Syntology ran

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 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 25 samples from 1 repository, 20 ran (15 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yunqing-me/RICK mentioned on GitHubpytorchMITSyntology: 25 samples, 20 ran (5 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

25 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 5 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
2ran; the contract check could not run
12ran
5unverified

Licence: 4 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yunqing-me/RICK. “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”. “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.

yunqing-me/RICK community (archive-listed) 25 samples, 20 ran (5 instrument-failed) · 5 unverified
all_gather in 119 papers distributed.py ran MIT (permissive) · ed03ba54397adbe4 · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-26
calculate_activation_statistics in 75 papers gan_metrics/fid_score.py ran fingerprinted MIT (permissive) · fa02bf7e7932504d · report fixture: signature act:ndarray/2/float · returned tuple · level recorded 2026-09-24
compute_pairwise_distances in 8 papers gan_metrics/precision_recall.py ran · honoured contract fingerprinted MIT (permissive) · af985ecf236605b0 · report fixture: signature X:ndarray/2/float, Y:ndarray/2/float · returned ndarray · level recorded 2026-09-22
d_logistic_loss in 15 papers
census: 2 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32 · arg 2: rank 1, kind float, dtype float32
train_dynamic_update_prune.py ran · our draft was wrong fingerprinted MIT (permissive) · 3651db4e5ae8d189 · report fixture: signature real_pred:Tensor/1/float, fake_pred:Tensor/1/float · returned Tensor · level recorded 2026-09-22
data_sampler in 17 papers train_dynamic_update_prune.py ran · our draft was wrong MIT (permissive) · dbb756dcd778f52f · report fixture: signature dataset:SimpleDataset/0/?, shuffle:bool/0/bool, distributed:bool/0/bool · returned RandomSampler · level recorded 2026-09-22
distances2radii gan_metrics/precision_recall.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 321ebed484cb3298 · report fixture: signature distances:ndarray/2/float, k:int/0/int · returned ndarray · level recorded 2026-09-22
get_kth_value in 8 papers gan_metrics/precision_recall.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · bcc716018b80b027 · report fixture: signature np_array:ndarray/1/float, k:int/0/int · returned float32 · level recorded 2026-09-22
get_parameter_number in 19 papers gan_training/utils_model_load.py ran MIT (permissive) · a6c491bc2737153b · report fixture: signature net:callable/0/?, name:str/0/str · returned int · level recorded 2026-09-24
is_url in 30 papers gan_training/checkpoints.py ran · violated contract MIT (permissive) · e39d881796e8d67e · report fixture: signature url:str/0/str · returned bool · level recorded 2026-09-24
load_part_model gan_training/utils_model_load.py ran · our draft was wrong MIT (permissive) · b3be36dffe58c81c · report fixture: signature m_fix:callable/0/?, m_ini:callable/0/? · returned SimpleModel · level recorded 2026-09-22
load_weights_without_module gan_training/utils_model_load.py ran MIT (permissive) · 2e7389cbf3256ad6 · report fixture: signature model:callable/0/?, dict:dict/0/?, strict:bool/0/bool · returned SimpleModel · level recorded 2026-09-24
polynomial_mmd in 7 papers gan_metrics/kid_score.py ran MIT (permissive) · 7405f2156522f874 · report fixture: signature codes_g:ndarray/2/float, codes_r:ndarray/2/float, degree:int/0/int, gamma:NoneType/0/?, coef0:int/0/int, var_at_m:NoneType/0/?, ret_var:bool/0/bool · returned tuple · level recorded 2026-09-25
reduce_loss_dict in 18 papers distributed.py ran MIT (permissive) · 5144ad456049f8ce · report fixture: signature loss_dict:dict/0/? · returned dict · level recorded 2026-09-26
reduce_sum in 34 papers
census: 4 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
distributed.py ran · honoured contract fingerprinted MIT (permissive) · 3f0a1105ef251d78 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
resize_and_convert in 7 papers prepare_data.py ran MIT (permissive) · 3d10a85c0ecf9e1a · report fixture: signature img:Image/0/?, size:tuple/1/int, resample:int/0/int, quality:int/0/int · returned bytes · level recorded 2026-09-24
resize_multiple in 7 papers prepare_data.py ran MIT (permissive) · f127271d8e059adf · report fixture: signature img:Image/0/?, sizes:tuple/1/int, resample:int/0/int, quality:int/0/int · returned list · level recorded 2026-09-24
resize_worker in 7 papers prepare_data.py ran MIT (permissive) · 45efc707c199b872 · report fixture: signature img_file:tuple/1/int, sizes:tuple/1/int, resample:int/0/int · returned tuple · level recorded 2026-09-24
rotate_mat non_leaking.py ran fingerprinted MIT (permissive) · a86cbcaf0967a531 · report fixture: signature theta:Tensor/1/float · returned Tensor · level recorded 2026-09-24
scale_mat non_leaking.py ran MIT (permissive) · 6817fba628078009 · report fixture: signature s_x:Tensor/1/float, s_y:Tensor/1/float · returned Tensor · level recorded 2026-09-24
translate_mat non_leaking.py ran MIT (permissive) · fdaede2415c5a2eb · report fixture: signature t_x:Tensor/1/float, t_y:Tensor/1/float · returned Tensor · level recorded 2026-09-24
calculate_frechet_distance in 119 papers gan_metrics/fid_score.py unverified MIT (permissive) · 0def50a351111624 · report
d_r1_loss in 10 papers train_dynamic_update_prune.py unverified MIT (permissive) here; the stored copy is pointer only · 1fb99d8f83eb27f3 · report
get_activations in 100 papers gan_metrics/fid_score.py unverified MIT (permissive) here; the stored copy is pointer only · 7b41327814ab3634 · report
get_activations in 100 papers gan_metrics/kid_score.py unverified MIT (permissive) · 8ab8902f4356f642 · report
polynomial_mmd_averages gan_metrics/kid_score.py unverified MIT (permissive) · d24b7925cdc50001 · report

Tasks

Image GenerationTransfer 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