SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.04488 · 2021

Low-Rank Subspaces in GANs

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2106.04488.json · badge: /api/ran/2106.04488.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
zhujiapeng/LowRankGAN canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
get_mask Ran
ran on a synthesized input
zhujiapeng/LowRankGAN/coordinate.py
code served (permissive licence) · get_code("4e8ae4e7d7c2c4a3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (32, 32) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Test case 1: using coordinates
image_size_1 = 32
coordinate_1 = (16, 16, 8, 8)  # center_x, center_y, crop_x, crop_y
seg_mask_1 = None
labels_1 = '1'

# Test case 2: using segmentation
image_size_2 = 32
coordinate_2 = None
seg_mask_2 = np.random.randint(0, 5, size=(32, 32), dtype=np.int32)
labels_2 = '12'

# We'll use the first test case for ARGS
ARGS = {
    'image_size': 32,
    'coordinate': (16, 16, 8, 8),
    'seg_mask': None,
    'labels': '1'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (32, 32) — shape (32, 32) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_mask_by_coordinates Ran
ran; our contract draft was wrong, not the code
zhujiapeng/LowRankGAN/coordinate.py
code served (permissive licence) · get_code("05c6bc0878c2290f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (32, 32) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct arguments for get_mask_by_coordinates
image_size = 32
coordinate = [10, 12, 8, 6]  # [center_x, center_y, crop_x, crop_y]

ARGS = {
    "image_size": image_size,
    "coordinate": coordinate,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (32, 32) — shape (32, 32) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_mask_by_segmentation Ran
ran, honoured the contract we drafted
zhujiapeng/LowRankGAN/coordinate.py
code served (permissive licence) · get_code("7ea70df01520bdf0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a segmentation mask with different label regions
seg_mask = np.array([
    [0, 0, 1, 1],
    [0, 2, 1, 2],
    [2, 2, 1, 1]
], dtype=np.int32)

# Define the label to extract
label = 1

ARGS = {
    "seg_mask": seg_mask,
    "label": label
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (3, 4) — shape (3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_template_from_path Ran
ran on a synthesized input
zhujiapeng/LowRankGAN/dnnlib/submission/submit.py
code served (permissive licence) · get_code("1f61e80b10011e25")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    "path": "C:\\Users\\Documents\\file.txt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
import_handler Ran
ran; our contract draft was wrong, not the code
zhujiapeng/LowRankGAN/dnnlib/tflib/network.py
pointer only (licence: MIT); the stored copy get_code serves, from isno0907/isodiff, is pointer only (licence: NONE) · get_code("9757ed6aa09ee00c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from isno0907/isodiff, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_path Not yet run
unverified (harvested, no recorded run)
zhujiapeng/LowRankGAN/dnnlib/submission/submit.py
code served (permissive licence) · get_code("5a6569d11eafa188")
How it ran

no invocation recorded.

get_path_from_template Not yet run
unverified (harvested, no recorded run)
zhujiapeng/LowRankGAN/dnnlib/submission/submit.py
code served (permissive licence) · get_code("9d5002fbab594877")
How it ran

no invocation recorded.

get_plugin Not yet run
unverified (harvested, no recorded run)
zhujiapeng/LowRankGAN/dnnlib/tflib/custom_ops.py
code served (permissive licence) · get_code("ae7f8c2a374edf1c")
How it ran

no invocation recorded.

resize_image Not yet run
unverified (harvested, no recorded run)
zhujiapeng/LowRankGAN/compute_jacobian.py
code served (permissive licence) · get_code("29bfeffdb65e32bc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
convert_path 1 other paper
1 dated earlier
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
get_mask_by_coordinates 1 other paper
1 later
2202.09649 (2022-02)
Region-Based Semantic Factorization in GANs
get_mask_by_segmentation 1 other paper
1 later
2202.09649 (2022-02)
Region-Based Semantic Factorization in GANs
get_path_from_template 1 other paper
1 dated earlier
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
get_plugin 1 other paper
1 later
2407.11451 (2024-07)
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
get_template_from_path 1 other paper
1 dated earlier
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
import_handler 1 other paper
1 later
2407.11451 (2024-07)
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The latent space of a Generative Adversarial Network (GAN) has been shown to encode rich semantics within some subspaces. To identify these subspaces, researchers typically analyze the statistical information from a collection of synthesized data, and the identified subspaces tend to control image attributes globally (i.e., manipulating an attribute causes the change of an entire image). By contrast, this work introduces low-rank subspaces that enable more precise control of GAN generation. Concretely, given an arbitrary image and a region of interest (e.g., eyes of face images), we manage to relate the latent space to the image region with the Jacobian matrix and then use low-rank factorization to discover steerable latent subspaces. There are three distinguishable strengths of our approach that can be aptly called LowRankGAN. First, compared to analytic algorithms in prior work, our low-rank factorization of Jacobians is able to find the low-dimensional representation of attribute manifold, making image editing more precise and controllable. Second, low-rank factorization naturally yields a null space of attributes such that moving the latent code within it only affects the outer region of interest. Therefore, local image editing can be simply achieved by projecting an attribute vector into the null space without relying on a spatial mask as existing methods do. Third, our method can robustly work with a local region from one image for analysis yet well generalize to other images, making it much easy to use in practice. Extensive experiments on state-of-the-art GAN models (including StyleGAN2 and BigGAN) trained on various datasets demonstrate the effectiveness of our LowRankGAN.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.04488")
get_code_for_paper("2106.04488")
have("2106.04488")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.04488.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.04488.svg)](https://syntology.ai/paper/2106.04488)

Connect an agent — have() is free.