Papers › Instance Selection for GANs

Instance Selection for GANs

30 Jul 2020NeurIPS 2020 12arXiv:2007.15255archive 2025-07-28

Terrance DeVries, Michal Drozdzal, Graham W. Taylor

Recent advances in Generative Adversarial Networks (GANs) have led to their widespread adoption for the purposes of generating high quality synthetic imagery. While capable of generating photo-realistic images, these models often produce unrealistic samples which fall outside of the data manifold. Several recently proposed techniques attempt to avoid spurious samples, either by rejecting them after generation, or by truncating the model's latent space. While effective, these methods are inefficient, as a large fraction of training time and model capacity are dedicated towards samples that will ultimately go unused. In this work we propose a novel approach to improve sample quality: altering the training dataset via instance selection before model training has taken place. By refining the empirical data distribution before training, we redirect model capacity towards high-density regions, which ultimately improves sample fidelity, lowers model capacity requirements, and significantly reduces training time. Code is available at https://github.com/uoguelph-mlrg/instance_selection_for_gans.

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 19 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 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: official repository: 4 samples from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 15 samples from 1 repository, 10 ran (5 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.

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 11 samples that ran has no recorded date.

uoguelph-mlrg/instance_selection_for_gans officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 1 ran (1 instrument-failed) · 3 unverified report
snap-research/3dgp mentioned on GitHubpytorchSyntology: 15 samples, 10 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.

Code Syntology ran Syntology

19 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 8 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.

5ran · honoured contract
4ran · our draft was wrong
2ran; the contract check could not run
8unverified

Licence: 19 of the 19 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. “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.

uoguelph-mlrg/instance_selection_for_gans official repository 4 samples, 1 ran (1 instrument-failed) · 3 unverified
get_embeddings_from_loader instance_selection.py ran; the contract check could not run (RAISES) licence not identified · pointer only · ff18ad392f262bf4 · report fixture: returned Tensor · level recorded, date not recorded
get_embedder in 88 papers instance_selection.py unverified licence not identified · pointer only · 8c0803be6096a937 · report
get_keep_indices instance_selection.py unverified licence not identified · pointer only · ed9e5e2f2a6ec523 · report
select_instances instance_selection.py unverified licence not identified · pointer only · 231ca68a3990599f · report
snap-research/3dgp community (archive-listed) 15 samples, 10 ran (5 instrument-failed) · 5 unverified
compute_patch_coords src/training/loss.py ran · honoured contract no licence file found · pointer only · d17ff266a8e14d95 · report fixture: signature patch_params:dict/0/?, resolution:int/0/int, align_corners:bool/0/bool, for_grid_sample:bool/0/bool · returned Tensor · level recorded 2026-09-22
create_patch_params_from_x_scales src/training/loss.py ran · our draft was wrong no licence file found · pointer only · 1a80415a81ba0286 · report fixture: signature patch_scales_x:ndarray/2/float, group_size:int/0/int, device:str/0/str · returned dict · level recorded 2026-09-22
extract_patches in 34 papers src/training/loss.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 83050978b92b849d · report fixture: signature x:Tensor/4/float, patch_params:dict/0/?, resolution:int/0/int · returned Tensor · level recorded 2026-09-22
generate_coords src/training/loss.py ran · honoured contract no licence file found · pointer only · dd340f2ccaa3b1c1 · report fixture: signature batch_size:int/0/int, img_size:int/0/int, device:str/0/str, align_corners:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_mean_angles_values src/training/loss.py ran · honoured contract no licence file found · pointer only · c8f0199beb8cdd4a · report fixture: signature angles_cfg:AnglesConfig/0/? · returned list · level recorded 2026-09-22
linear_schedule in 26 papers src/training/loss.py ran · honoured contract fingerprinted no licence file found · pointer only · 97c1685bb8978f57 · report fixture: signature step:int/0/int, val_start:float/0/float, val_end:float/0/float, period:int/0/int, start_step:int/0/int · returned float · level recorded 2026-09-22
sample_patch_params src/training/loss.py ran · our draft was wrong no licence file found · pointer only · fec2702e4e6b4e2a · report fixture: signature batch_size:int/0/int, patch_cfg:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-22
sample_patch_params_beta src/training/loss.py ran · our draft was wrong no licence file found · pointer only · 1e37173d536f5edf · report fixture: signature batch_size:int/0/int, min_scale:float/0/float, max_scale:float/0/float, alpha:float/0/float, beta:float/0/float, group_size:int/0/int, device:str/0/str · returned dict · level recorded 2026-09-22
sample_patch_params_uniform src/training/loss.py ran · our draft was wrong no licence file found · pointer only · b7fba8479ac80873 · report fixture: signature batch_size:int/0/int, min_scale:float/0/float, max_scale:float/0/float, discrete_support:NoneType/0/?, group_size:int/0/int, device:str/0/str · returned dict · level recorded 2026-09-22
sample_random_c src/training/loss.py ran · honoured contract no licence file found · pointer only · 6637867e242d3dab · report fixture: signature batch_size:int/0/int, c_dim:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
EasyDict src/training/loss.py unverified no licence file found · pointer only · eb7e5d8169d00081 · report
Loss in 19 papers src/training/loss.py unverified no licence file found · pointer only · cec2fa3cb3bf036c · report
StyleGAN2Loss src/training/loss.py unverified no licence file found · pointer only · 80ae2ec4a5e4df48 · report
TensorGroup src/training/loss.py unverified no licence file found · pointer only · 8967de870e98579f · report
maybe_blur src/training/loss.py unverified no licence file found · pointer only · 8558d52802c25638 · 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. 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 instance selection for GANs (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for instance selection for GANs (graph method: instance selection for GANs). 15 bricks; individually on a fixture: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. StyleGAN2Loss entry · level 0 · unverified · 80ae2ec4a5e4df48
  2. EasyDict helper · level 0 · unverified · eb7e5d8169d00081
  3. Loss helper · level 0 · unverified · cec2fa3cb3bf036c
  4. TensorGroup helper · level 0 · unverified · 8967de870e98579f
  5. extract_patches helper · level 1 · ran; the contract check could not run (RAISES) · 83050978b92b849d
  6. get_mean_angles_values helper · level 1 · ran · honoured contract · c8f0199beb8cdd4a
  7. linear_schedule helper · level 1 · ran · honoured contract · 97c1685bb8978f57
  8. maybe_blur helper · level 0 · unverified · 8558d52802c25638
  9. sample_patch_params helper · level 1 · ran · our draft was wrong · fec2702e4e6b4e2a
  10. sample_random_c helper · level 1 · ran · honoured contract · 6637867e242d3dab
  11. compute_patch_coords helper · level 1 · ran · honoured contract · d17ff266a8e14d95
  12. sample_patch_params_beta helper · level 1 · ran · our draft was wrong · 1e37173d536f5edf
  13. sample_patch_params_uniform helper · level 1 · ran · our draft was wrong · b7fba8479ac80873
  14. generate_coords helper · level 1 · ran · honoured contract · dd340f2ccaa3b1c1
  15. create_patch_params_from_x_scales helper · level 1 · ran · our draft was wrong · 1a80415a81ba0286

harvested Assembly for instance selection for GANs (graph method: instance selection for GANs). 4 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. select_instances entry · level 0 · unverified · 231ca68a3990599f
  2. get_embedder helper · level 0 · unverified · 8c0803be6096a937
  3. get_embeddings_from_loader helper · level 1 · ran; the contract check could not run (RAISES) · ff18ad392f262bf4
  4. get_keep_indices helper · level 0 · unverified · ed9e5e2f2a6ec523

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="2007.15255") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Image Generation ImageNet 128x128 BigGAN + instance selection FID 9.61 #16 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 128x128 BigGAN + instance selection Inception score 114.32 #16 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 64x64 SAGAN + instance selection FID 9.07 #2 of 4 Archive leaderboard report
Conditional Image Generation ImageNet 64x64 SAGAN + instance selection Inception score 37.1 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAdamBatch NormalizationBigGANConditional Batch NormalizationConvolutionDense ConnectionsEarly StoppingFeedforward NetworkGAN Hinge LossLinear LayerNon-Local BlockNon-Local OperationOff-Diagonal Orthogonal RegularizationProjection DiscriminatorReLUResidual BlockResidual ConnectionSAGANSoftmaxSpectral NormalizationTTURTruncation Trick

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