Papers › Content-Aware GAN Compression

Content-Aware GAN Compression

6 Apr 2021CVPR 2021 1arXiv:2104.02244archive 2025-07-28

Yuchen Liu, Zhixin Shu, Yijun Li, Zhe Lin, Federico Perazzi, S. Y. Kung

Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders their efficient deployment on edge devices. Directly applying generic compression approaches yields poor results on GANs, which motivates a number of recent GAN compression works. While prior works mainly accelerate conditional GANs, e.g., pix2pix and CycleGAN, compressing state-of-the-art unconditional GANs has rarely been explored and is more challenging. In this paper, we propose novel approaches for unconditional GAN compression. We first introduce effective channel pruning and knowledge distillation schemes specialized for unconditional GANs. We then propose a novel content-aware method to guide the processes of both pruning and distillation. With content-awareness, we can effectively prune channels that are unimportant to the contents of interest, e.g., human faces, and focus our distillation on these regions, which significantly enhances the distillation quality. On StyleGAN2 and SN-GAN, we achieve a substantial improvement over the state-of-the-art compression method. Notably, we reduce the FLOPs of StyleGAN2 by 11x with visually negligible image quality loss compared to the full-size model. More interestingly, when applied to various image manipulation tasks, our compressed model forms a smoother and better disentangled latent manifold, making it more effective for image editing.

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 16 code samples harvested from 1 repository linked to this paper: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 9 ran (6 with no instrument failure; 3 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.

lychenyoko/content-aware-gan-compression officialmentioned on GitHubpytorchSyntology: 16 samples, 9 ran (3 instrument-failed) · 7 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

16 samples harvested: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 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.

1ran · violated contract
3ran · our draft was wrong
5ran
7unverified

Licence: 0 of the 16 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 lychenyoko/content-aware-gan-compression. “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 4 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.

lychenyoko/content-aware-gan-compression official repository 16 samples, 9 ran (3 instrument-failed) · 7 unverified
AttentionRefinementModule Util/content_aware_pruning.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1251cde09a254488 · report fixture: returned AttentionRefinementModule · level recorded 2026-09-22
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
Util/content_aware_pruning.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 103e4a171a95689b · report fixture: returned BasicBlock · level recorded 2026-09-22
BiSeNetOutput Util/content_aware_pruning.py ran · metamorphic tier: deterministic MIT (permissive) · 65ffe5a35cd297ca · report fixture: returned BiSeNetOutput · level recorded 2026-09-22
ConvBNReLU in 16 papers Util/content_aware_pruning.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 199ed6b9f3c73292 · report fixture: returned ConvBNReLU · level recorded 2026-09-22
Extract_Face_Mask Util/content_aware_pruning.py ran · our draft was wrong MIT (permissive) · cc4b8cc6c40c39f8 · report fixture: signature pil_image:Image/0/?, parsing_net:callable/0/?, to_tensor:callable/0/?, device:str/0/str · returned ndarray · level recorded 2026-09-22
FeatureFusionModule Util/content_aware_pruning.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1ef6184686bbc091 · report fixture: returned FeatureFusionModule · level recorded 2026-09-22
Get_Salt_Pepper_Noisy_Image Util/content_aware_pruning.py ran · violated contract fingerprinted MIT (permissive) · c5f90f064c23fc80 · report fixture: signature img_tensor:Tensor/4/float, mask:ndarray/2/bool, prob:float/0/float · returned Tensor · level recorded 2026-09-22
conv3x3 in 1,376 papers Util/content_aware_pruning.py ran · our draft was wrong MIT (permissive) · dd1114865f06f0fd · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
create_layer_basic in 19 papers Util/content_aware_pruning.py ran · our draft was wrong MIT (permissive) · c7601557922b3f9c · report fixture: signature in_chan:int/0/int, out_chan:int/0/int, bnum:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
BiSeNet Util/content_aware_pruning.py unverified MIT (permissive) · e4ce9b02d8344f92 · report
ContextPath Util/content_aware_pruning.py unverified MIT (permissive) · 85e291ec32606b2e · report
Convert_Tensor_To_Image Util/content_aware_pruning.py unverified MIT (permissive) · 5898b758c56bf090 · report
Get_Content_Aware_Pruning_Score Util/content_aware_pruning.py unverified MIT (permissive) · aca93853a087107e · report
Get_Parsing_Net Util/content_aware_pruning.py unverified MIT (permissive) · 059c2e41e6ee7e1d · report
Get_Weight_Gradient Util/content_aware_pruning.py unverified MIT (permissive) · 9269f9c755fff863 · report
Resnet18 Util/content_aware_pruning.py unverified MIT (permissive) · f728dc2f00391366 · 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 content-aware method (graph method: content-aware method). 16 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. Get_Content_Aware_Pruning_Score entry · level 0 · unverified · aca93853a087107e
  2. Convert_Tensor_To_Image helper · level 0 · unverified · 5898b758c56bf090
  3. Extract_Face_Mask helper · level 1 · ran · our draft was wrong · cc4b8cc6c40c39f8
  4. Get_Parsing_Net helper · level 0 · unverified · 059c2e41e6ee7e1d
  5. Get_Salt_Pepper_Noisy_Image helper · level 1 · ran · violated contract · c5f90f064c23fc80
  6. Get_Weight_Gradient helper · level 0 · unverified · 9269f9c755fff863
  7. BiSeNet helper · level 0 · unverified · e4ce9b02d8344f92
  8. BiSeNetOutput helper · level 1 · ran · 65ffe5a35cd297ca
  9. ContextPath helper · level 0 · unverified · 85e291ec32606b2e
  10. FeatureFusionModule helper · level 1 · ran · 1ef6184686bbc091
  11. ConvBNReLU helper · level 1 · ran · 199ed6b9f3c73292
  12. AttentionRefinementModule helper · level 1 · ran · 1251cde09a254488
  13. Resnet18 helper · level 0 · unverified · f728dc2f00391366
  14. create_layer_basic helper · level 1 · ran · our draft was wrong · c7601557922b3f9c
  15. BasicBlock helper · level 1 · ran · 103e4a171a95689b
  16. conv3x3 helper · level 1 · ran · our draft was wrong · dd1114865f06f0fd

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="2104.02244") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image GenerationImage ManipulationKnowledge Distillation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationConcatenated Skip ConnectionConvolutionCycle Consistency LossDropoutGAN Least Squares LossInstance NormalizationKnowledge DistillationPatchGANPath Length RegularizationPix2PixPruningR1 RegularizationReLUResidual BlockResidual ConnectionSigmoid ActivationStyleGAN2Tanh ActivationWeight Demodulation

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