SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1701.01081 · 2017

SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 2 failures of our instrument; 0 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/1701.01081.json · badge: /api/ran/1701.01081.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
imatge-upc/saliency-2019-SalBCE community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
augmentData Ran
ran on a synthesized input
imatge-upc/saliency-2019-SalBCE/src/dataloader/datasetDHF1K.py
code served (permissive licence) · get_code("af7c99315a3cb578")
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 tuple. 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 numpy as np

# Create a small test image (height, width, channels)
image = np.random.randint(0, 256, size=(4, 5, 3), dtype=np.uint8)

# Create a small saliency map (height, width)
saliency = np.random.rand(4, 5).astype(np.float32)

ARGS = {
    "image": image,
    "saliency": saliency
}
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 tuple — a tuple output has no array shape of its own; none is 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
imageProcessing Ran
ran on a synthesized input
imatge-upc/saliency-2019-SalBCE/src/dataloader/datasetSALICON.py
code served (permissive licence) · get_code("59586ad0baafd71a")
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 tuple. 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 cv2
import numpy as np
from random import randint
from scipy import ndimage
import torch

torch.manual_seed(0)

# Create a small stand-in image: height=480, width=640, 3 channels (BGR)
image = np.random.rand(480, 640, 3).astype(np.float32) * 255

# Create a small stand-in saliency map: height=480, width=640, 1 channel
saliency = np.random.rand(480, 640).astype(np.float32) * 255

ARGS = {
    "image": image,
    "saliency": saliency,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
imageProcessing Ran
ran on a synthesized input
imatge-upc/saliency-2019-SalBCE/src/dataloader/datasetSALICON_adv.py
code served (permissive licence) · get_code("36e1d7722f053ab7")
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 tuple. 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 cv2
import numpy as np
import torch

torch.manual_seed(0)

# Create a small test image: (256, 192, 3) for BGR format
# Using distinct dimension sizes: 256 height, 192 width, 3 channels
image = np.random.randint(0, 256, size=(256, 192, 3), dtype=np.uint8)

# Create a small saliency map: (256, 192, 1)
saliency = np.random.randint(0, 256, size=(256, 192, 1), dtype=np.uint8)

ARGS = {
    'image': image,
    'saliency': saliency
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
img_name Ran
ran on a synthesized input
imatge-upc/saliency-2019-SalBCE/src/dataloader/datasetDHF1K.py
code served (permissive licence) · get_code("459f8d7969d62144")
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
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - name: a string that can be split by '.' and the first part should be convertible to int
# - num: an integer used for comparison and division

ARGS = {
    'name': '0042.png',
    'num': 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
match_hist Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
imatge-upc/saliency-2019-SalBCE/src/evaluation/tools.py
pointer only (licence: MIT); the stored copy get_code serves, from hkust-nisl/oat_eccv24, is pointer only (licence: NONE) · get_code("039e9f0f0dfbfaca")
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 hkust-nisl/oat_eccv24, 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.

normalize Ran
ran; our contract draft was wrong, not the code
imatge-upc/saliency-2019-SalBCE/src/evaluation/tools.py
pointer only (licence: MIT); the stored copy get_code serves, from hkust-nisl/oat_eccv24, is pointer only (licence: NONE) · get_code("d3d86d1943c5ac37")
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 hkust-nisl/oat_eccv24, 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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 4 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
match_hist 1 other paper
1 later
2407.13335 (2024-07)
OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction
normalize 1 other paper
1 later
2407.13335 (2024-07)
OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction

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

We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE. Our results can be reproduced with the source code and trained models available at https://imatge-upc.github.io/saliency-salgan-2017/.

For agents

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

get_harvested_code_for_paper("1701.01081")
get_code_for_paper("1701.01081")
have("1701.01081")

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

curl https://syntology.ai/api/ran/1701.01081.json

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

[![Syntology run record](https://syntology.ai/api/ran/1701.01081.svg)](https://syntology.ai/paper/1701.01081)

Connect an agent — have() is free.