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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2304.07574")

Code

Syntology Ran 8 of 25 code samples harvested from 1 repository linked to this paper; 17 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 2 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: community (archive-listed): 25 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yunqing-me/RICK mentioned on GitHubpytorchMIT 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; 8 ran; 1 honoured the contract we drafted; 17 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
2ran · fixture could not drive it
2ran
17unverified

Licence: 0 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 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

compute_pairwise_distances yunqing-me/RICK/gan_metrics/precision_recall.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · af985ecf236605b0 · report
d_logistic_loss yunqing-me/RICK/train_dynamic_update_prune.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 3651db4e5ae8d189 · report
data_sampler yunqing-me/RICK/train_dynamic_update_prune.py community (archive-listed) ran · our draft was wrong MIT (permissive) · dbb756dcd778f52f · report
distances2radii yunqing-me/RICK/gan_metrics/precision_recall.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 321ebed484cb3298 · report
get_kth_value yunqing-me/RICK/gan_metrics/precision_recall.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · bcc716018b80b027 · report
is_url yunqing-me/RICK/gan_training/checkpoints.py community (archive-listed) ran MIT (permissive) · e39d881796e8d67e · report
load_part_model yunqing-me/RICK/gan_training/utils_model_load.py community (archive-listed) ran · our draft was wrong MIT (permissive) · b3be36dffe58c81c · report
reduce_sum yunqing-me/RICK/distributed.py community (archive-listed) ran fingerprinted MIT (permissive) · 3f0a1105ef251d78 · report
all_gather yunqing-me/RICK/distributed.py community (archive-listed) unverified MIT (permissive) · ed03ba54397adbe4 · report
calculate_activation_statistics yunqing-me/RICK/gan_metrics/fid_score.py community (archive-listed) unverified MIT (permissive) · fa02bf7e7932504d · report
calculate_frechet_distance yunqing-me/RICK/gan_metrics/fid_score.py community (archive-listed) unverified MIT (permissive) · 0def50a351111624 · report
d_r1_loss yunqing-me/RICK/train_dynamic_update_prune.py community (archive-listed) unverified MIT (permissive) · 1fb99d8f83eb27f3 · report
get_activations yunqing-me/RICK/gan_metrics/fid_score.py community (archive-listed) unverified MIT (permissive) · 7b41327814ab3634 · report
get_activations yunqing-me/RICK/gan_metrics/kid_score.py community (archive-listed) unverified MIT (permissive) · 8ab8902f4356f642 · report
get_parameter_number yunqing-me/RICK/gan_training/utils_model_load.py community (archive-listed) unverified MIT (permissive) · a6c491bc2737153b · report
load_weights_without_module yunqing-me/RICK/gan_training/utils_model_load.py community (archive-listed) unverified MIT (permissive) · 2e7389cbf3256ad6 · report
polynomial_mmd yunqing-me/RICK/gan_metrics/kid_score.py community (archive-listed) unverified MIT (permissive) · 7405f2156522f874 · report
polynomial_mmd_averages yunqing-me/RICK/gan_metrics/kid_score.py community (archive-listed) unverified MIT (permissive) · d24b7925cdc50001 · report
reduce_loss_dict yunqing-me/RICK/distributed.py community (archive-listed) unverified MIT (permissive) · 5144ad456049f8ce · report
resize_and_convert yunqing-me/RICK/prepare_data.py community (archive-listed) unverified MIT (permissive) · 3d10a85c0ecf9e1a · report
resize_multiple yunqing-me/RICK/prepare_data.py community (archive-listed) unverified MIT (permissive) · f127271d8e059adf · report
resize_worker yunqing-me/RICK/prepare_data.py community (archive-listed) unverified MIT (permissive) · 45efc707c199b872 · report
rotate_mat yunqing-me/RICK/non_leaking.py community (archive-listed) unverified MIT (permissive) · a86cbcaf0967a531 · report
scale_mat yunqing-me/RICK/non_leaking.py community (archive-listed) unverified MIT (permissive) · 6817fba628078009 · report
translate_mat yunqing-me/RICK/non_leaking.py community (archive-listed) unverified MIT (permissive) · fdaede2415c5a2eb · 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