Papers › Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

17 Aug 2021ICCV 2021 10arXiv:2108.07668archive 2025-07-28

Yuxiang Wei, Yupeng Shi, Xiao Liu, Zhilong Ji, Yuan Gao, Zhongqin Wu, WangMeng Zuo

Unsupervised disentanglement learning is a crucial issue for understanding and exploiting deep generative models. Recently, SeFa tries to find latent disentangled directions by performing SVD on the first projection of a pre-trained GAN. However, it is only applied to the first layer and works in a post-processing way. Hessian Penalty minimizes the off-diagonal entries of the output's Hessian matrix to facilitate disentanglement, and can be applied to multi-layers.However, it constrains each entry of output independently, making it not sufficient in disentangling the latent directions (e.g., shape, size, rotation, etc.) of spatially correlated variations. In this paper, we propose a simple Orthogonal Jacobian Regularization (OroJaR) to encourage deep generative model to learn disentangled representations. It simply encourages the variation of output caused by perturbations on different latent dimensions to be orthogonal, and the Jacobian with respect to the input is calculated to represent this variation. We show that our OroJaR also encourages the output's Hessian matrix to be diagonal in an indirect manner. In contrast to the Hessian Penalty, our OroJaR constrains the output in a holistic way, making it very effective in disentangling latent dimensions corresponding to spatially correlated variations. Quantitative and qualitative experimental results show that our method is effective in disentangled and controllable image generation, and performs favorably against the state-of-the-art methods. Our code is available at https://github.com/csyxwei/OroJaR

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 21 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 11 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 20 ran (9 with no instrument failure; 11 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 20 samples that ran have no recorded date.

csyxwei/orojar officialmentioned in papermentioned on GitHubpytorchBSD-2-ClauseSyntology: 21 samples, 20 ran (11 instrument-failed) · 1 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

21 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 11 where Syntology's instrument failed) · 1 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.

1ran · honoured contract
10ran · our draft was wrong
1ran; the contract check could not run
8ran
1unverified

Licence: 6 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 csyxwei/orojar. “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.

csyxwei/orojar official repository 21 samples, 20 ran (11 instrument-failed) · 1 unverified
D_arch in 21 papers biggan_discovery/BigGAN.py ran · our draft was wrong BSD-2-Clause (permissive) here; the stored copy is pointer only · 85eb95cce203dfc7 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded, date not recorded
D_arch in 21 papers biggan_discovery/BigGANdeep.py ran BSD-2-Clause (permissive) · a99a05ac52533be9 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded 2026-09-25
G_arch in 22 papers biggan_discovery/BigGAN.py ran · our draft was wrong BSD-2-Clause (permissive) here; the stored copy is pointer only · e8c308c9283407d7 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded, date not recorded
G_arch in 22 papers biggan_discovery/BigGANdeep.py ran BSD-2-Clause (permissive) · 44d6a6343f6eb182 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded 2026-09-25
build_job_name progan_experiments/train_orojar.py ran BSD-2-Clause (permissive) · 4da4d6bc0bd3244a · report fixture: signature opt:Options/0/? · returned str · level recorded 2026-09-25
first_directional_derivative biggan_discovery/orojar.py ran BSD-2-Clause (permissive) · 09e8b81f44dc0143 · report fixture: signature G:callable/0/?, z:Tensor/2/float, c:Tensor/2/float, x:Tensor/2/float, G_z:Tensor/2/float, epsilon:float/0/float, w:Tensor/2/float, Q:Tensor/2/float · returned Tensor · level recorded 2026-09-25
get_current_hessian_penalty_loss_weight progan_experiments/training/orojar.py ran fingerprinted BSD-2-Clause (permissive) · 84a7e309cd2bf8f6 · report fixture: signature max_lambda:float/0/float, hp_start_iter:int/0/int, t:int/0/int, T:int/0/int · returned float · level recorded 2026-09-25
gram_schmidt in 32 papers biggan_discovery/layers.py ran · our draft was wrong BSD-2-Clause (permissive) here; the stored copy is pointer only · c41836f3e51fa8f1 · report fixture: signature x:Tensor/2/float, ys:list/1/Tensor · returned Tensor · level recorded 2026-09-22
listify in 14 papers biggan_discovery/orojar.py ran · honoured contract fingerprinted BSD-2-Clause (permissive) here; the stored copy is pointer only · 47b42795fd222ceb · report fixture: signature x:int/0/int · returned list · level recorded 2026-09-22
loss_dcgan_dis in 13 papers biggan_discovery/losses.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) · 982a26492dc6b7fb · report fixture: signature dis_fake:Tensor/2/float, dis_real:Tensor/2/float · returned tuple · level recorded 2026-09-25
loss_dcgan_gen in 13 papers biggan_discovery/losses.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) · 6c34831223553b6f · report fixture: signature dis_fake:Tensor/2/float · returned Tensor · level recorded 2026-09-25
loss_hinge_dis in 14 papers biggan_discovery/losses.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) · 290cd37ab0098d5c · report fixture: signature dis_fake:Tensor/2/float, dis_real:Tensor/2/float · returned tuple · level recorded 2026-09-25
multi_layer_first_directional_derivative orojar_pytorch.py ran · our draft was wrong BSD-2-Clause (permissive) · f6b513df7a8f90bf · report fixture: signature G:callable/0/?, z:Tensor/2/float, x:Tensor/2/float, G_z:Tensor/2/float, epsilon:float/0/float · returned list · level recorded 2026-09-22
multi_stack_var_and_reduce orojar_pytorch.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed BSD-2-Clause (permissive) · 16fa0b0146a66a69 · report fixture: signature fdds:list/1/list, reduction:callable/0/?, return_separately:bool/0/bool · returned Tensor · level recorded 2026-09-22
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket
biggan_discovery/layers.py ran fingerprinted BSD-2-Clause (permissive) · 2de3863ec32c1c1f · report fixture: signature rr:Tensor/2/float · returned Tensor · level recorded 2026-09-25
orojar orojar_pytorch.py ran · our draft was wrong BSD-2-Clause (permissive) · a2ed9ad66857123a · report fixture: signature G:callable/0/?, z:Tensor/2/float, k:int/0/int, epsilon:float/0/float, reduction:callable/0/?, return_separately:bool/0/bool, G_z:list/1/Tensor, G_kwargs:dict/0/? · returned Tensor · level recorded 2026-09-22
orojar orojar_pytorch.py ran BSD-2-Clause (permissive) · ff29a0906a2963fb · report fixture: signature G:callable/0/?, z:Tensor/2/float, k:int/0/int, epsilon:float/0/float, reduction:callable/0/?, return_separately:bool/0/bool, G_z:list/1/Tensor · returned Tensor · level recorded 2026-09-25
rademacher in 5 papers orojar_pytorch.py ran · our draft was wrong BSD-2-Clause (permissive) here; the stored copy is pointer only · 8de600fe2220e241 · report fixture: signature shape:tuple/1/int, device:str/0/str · returned Tensor · level recorded 2026-09-22
rademacher in 5 papers biggan_discovery/orojar.py ran BSD-2-Clause (permissive) · 58800b4db4b14ffd · report fixture: signature shape:tuple/1/int, gpu:bool/0/bool · returned Tensor · level recorded 2026-09-25
stack_var_and_reduce orojar_pytorch.py ran · our draft was wrong BSD-2-Clause (permissive) · 97ecfd58b1dab254 · report fixture: signature list_of_activations:list/1/Tensor, reduction:callable/0/? · returned Tensor · level recorded 2026-09-22
proj in 38 papers biggan_discovery/layers.py unverified BSD-2-Clause (permissive) here; the stored copy is pointer only · 4015ab1f3ab9b881 · 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 Orthogonal Jacobian Regularization (OroJaR) (graph method: Orthogonal Jacobian Regularization (OroJaR)). 6 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. orojar entry · level 1 · ran · our draft was wrong · a2ed9ad66857123a
  2. multi_layer_first_directional_derivative helper · level 1 · ran · our draft was wrong · f6b513df7a8f90bf
  3. multi_stack_var_and_reduce loss · level 1 · ran; the contract check could not run (RAISES) · 16fa0b0146a66a69
  4. rademacher helper · level 1 · ran · our draft was wrong · 8de600fe2220e241
  5. listify helper · level 1 · ran · honoured contract · 47b42795fd222ceb
  6. stack_var_and_reduce loss · level 1 · ran · our draft was wrong · 97ecfd58b1dab254

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="2108.07668") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DisentanglementImage Generation

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