SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.03593 · 2021

TranSalNet: Towards perceptually relevant visual saliency prediction

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 1 has no contract verdict; 7 failures of our instrument; 3 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/2110.03593.json · badge: /api/ran/2110.03593.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
ljovo/transalnet canonical (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
ljovo/transalnet/utils/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
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 medaitech/scrd4ad, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
ljovo/transalnet/utils/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
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 medaitech/scrd4ad, 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.

loss_CC Ran
ran; our contract draft was wrong, not the code
ljovo/transalnet/utils/loss_function.py
code served (permissive licence) · get_code("774d792a6525842a")
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 Tensor, ndim 0, dtype family float, shape () 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 torch as t

t.manual_seed(0)

# Create small tensor arguments for the loss_CC function
# The function performs correlation coefficient calculation between two maps
# Both pred_map and gt_map are used with: mean, subtraction, multiplication, sum, sqrt
# They should be similar shapes for a meaningful correlation

pred_map = t.randn(2, 4)
gt_map = t.randn(2, 4)

ARGS = {
    "pred_map": pred_map,
    "gt_map": gt_map,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
loss_KLdiv Ran
ran; our contract draft was wrong, not the code
ljovo/transalnet/utils/loss_function.py
code served (permissive licence) · get_code("e9183c75893d49f0")
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 Tensor, ndim 0, dtype family float, shape () 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 torch as t

t.manual_seed(0)

# Create small prediction and ground truth maps
# The function expects tensors that will be normalized via t.sum()
# Using distinct dimensions: batch=2, spatial=4
pred_map = t.rand(2, 4)
gt_map = t.rand(2, 4)

ARGS = {
    "pred_map": pred_map,
    "gt_map": gt_map,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
loss_similarity Ran
ran; our contract draft was wrong, not the code
ljovo/transalnet/utils/loss_function.py
code served (permissive licence) · get_code("9596d79dd2070fff")
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 Tensor, ndim 0, dtype family float, shape () 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 torch as t

t.manual_seed(0)

# Create small prediction and ground truth maps
# The function expects tensors that can be normalized and summed
pred_map = t.randn(2, 4)
gt_map = t.randn(2, 4)

ARGS = {
    "pred_map": pred_map,
    "gt_map": gt_map,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
postprocess_img Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ljovo/transalnet/utils/data_process.py
code served (permissive licence) · get_code("ebfa76e7f72447ce")
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 (100, 80) 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 cv2
import numpy as np
import tempfile
import os

# Create a temporary directory and a small test image
temp_dir = tempfile.mkdtemp()
org_path = os.path.join(temp_dir, "test_image.png")

# Create and save a small grayscale image (100x80 pixels)
org_img = np.random.randint(0, 256, (100, 80), dtype=np.uint8)
cv2.imwrite(org_path, org_img)

# Create a prediction array with different dimensions (50x40)
# This will test the resizing and cropping logic
pred = np.random.randint(0, 256, (50, 40), dtype=np.uint8)

ARGS = {
    "pred": pred,
    "org_dir": org_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 (100, 80) — shape (100, 80) 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
preprocess_img Ran
ran on a synthesized input
ljovo/transalnet/utils/data_process.py
code served (permissive licence) · get_code("ed2103d493d0a213")
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 3, dtype family int, shape (288, 384, 3) 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 cv2
import numpy as np
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
img_path = os.path.join(temp_dir, "test_image.png")

# Create a simple test image (100x150 RGB)
test_img = np.random.randint(0, 256, (100, 150, 3), dtype=np.uint8)
cv2.imwrite(img_path, test_img)

ARGS = {
    "img_dir": img_path,
    "channels": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (288, 384, 3) — shape (288, 384, 3) 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
resnet18 Ran
ran; our contract draft was wrong, not the code
ljovo/transalnet/utils/resnet.py
code served (permissive licence) · get_code("6823079f294e25ae")
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 ResNet. 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 torch.nn as nn

torch.manual_seed(0)

# Define a minimal stand-in for the ResNet function signature
# We need to construct arguments for resnet18 which is a constructor function

def resnet18(pretrained: bool = False, progress: bool = True, **kwargs):
    """Constructs a ResNet-18 model."""
    return ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)

# Now construct valid arguments for resnet18
ARGS = {
    'pretrained': False,
    'progress': True,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
densenet121 Not yet run
unverified (harvested, no recorded run)
ljovo/transalnet/utils/densenet.py
code served (permissive licence) · get_code("8fbb6e8ffe5752f5")
How it ran

no invocation recorded.

densenet161 Not yet run
unverified (harvested, no recorded run)
ljovo/transalnet/utils/densenet.py
code served (permissive licence) · get_code("84c7817fbe252d76")
How it ran

no invocation recorded.

densenet169 Not yet run
unverified (harvested, no recorded run)
ljovo/transalnet/utils/densenet.py
code served (permissive licence) · get_code("d14cf2b8e9e2a0ef")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 10 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 10 later) and 1 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
conv1x1 112 other papers
14 dated earlier, 2 the same month, 96 later · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3 111 other papers
12 dated earlier, 2 the same month, 97 later · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
resnet18 36 other papers
6 dated earlier, 2 the same month, 28 later
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2002.09564 (2020-02)
Towards Robust and Reproducible Active Learning Using Neural Networks
2003.04297 (2020-03)
Improved Baselines with Momentum Contrastive Learning
and 33 more not named here
densenet121 8 other papers
4 dated earlier, 4 later
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
1912.00385 (2019-12)
The Group Loss for Deep Metric Learning
2010.11742 (2020-10)
Learning Black-Box Attackers with Transferable Priors and Query Feedback
and 5 more not named here
densenet161 8 other papers
5 dated earlier, 3 later
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
1905.11926 (2019-05)
Network Deconvolution
1912.00385 (2019-12)
The Group Loss for Deep Metric Learning
and 5 more not named here
densenet169 8 other papers
5 dated earlier, 3 later
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
1905.11926 (2019-05)
Network Deconvolution
1912.00385 (2019-12)
The Group Loss for Deep Metric Learning
and 5 more not named here
loss_CC 1 other paper
1 later
2406.17815 (2024-06)
SUM: Saliency Unification through Mamba for Visual Attention Modeling
loss_KLdiv 1 other paper
1 later
2406.17815 (2024-06)
SUM: Saliency Unification through Mamba for Visual Attention Modeling
loss_similarity 1 other paper
1 later
2406.17815 (2024-06)
SUM: Saliency Unification through Mamba for Visual Attention Modeling
postprocess_img 1 other paper
1 later
2406.17815 (2024-06)
SUM: Saliency Unification through Mamba for Visual Attention Modeling

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

Visual saliency prediction using transformers - Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human cortex remains an academic challenge. It is critical to integrate properties of human vision into the design of CNN architectures, leading to perceptually more relevant saliency prediction. Due to the inherent inductive biases of CNN architectures, there is a lack of sufficient long-range contextual encoding capacity. This hinders CNN-based saliency models from capturing properties that emulate viewing behaviour of humans. Transformers have shown great potential in encoding long-range information by leveraging the self-attention mechanism. In this paper, we propose a novel saliency model that integrates transformer components to CNNs to capture the long-range contextual visual information. Experimental results show that the transformers provide added value to saliency prediction, enhancing its perceptual relevance in the performance. Our proposed saliency model using transformers has achieved superior results on public benchmarks and competitions for saliency prediction models. The source code of our proposed saliency model TranSalNet is available at: https://github.com/LJOVO/TranSalNet

For agents

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

get_harvested_code_for_paper("2110.03593")
get_code_for_paper("2110.03593")
have("2110.03593")

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

curl https://syntology.ai/api/ran/2110.03593.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.03593.svg)](https://syntology.ai/paper/2110.03593)

Connect an agent — have() is free.