SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1609.01064 · 2016

A Deep Multi-Level Network for Saliency Prediction

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 0 failures of our instrument; 1 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/1609.01064.json · badge: /api/ran/1609.01064.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
marcellacornia/mlnet canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
get_weights_vgg16 Ran
ran on a synthesized input
marcellacornia/mlnet/model.py
code served (permissive licence) · get_code("d6eae2d1e285d247")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 h5py
import tempfile
import os

torch.manual_seed(0)

# Create a temporary HDF5 file to serve as the dict-like object 'f'
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.h5")

with h5py.File(temp_file, "w") as f:
    # Create layer_0 group
    layer_0 = f.create_group("layer_0")
    
    # Set the number of parameters attribute
    layer_0.attrs["nb_params"] = 3
    
    # Create parameter datasets
    layer_0.create_dataset("param_0", data=[1.0, 2.0, 3.0, 4.0])
    layer_0.create_dataset("param_1", data=[5.0, 6.0, 7.0, 8.0])
    layer_0.create_dataset("param_2", data=[9.0, 10.0, 11.0, 12.0])

# Open the file again to use it as an argument
f = h5py.File(temp_file, "r")
id = 0

ARGS = {
    "f": f,
    "id": id
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
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
padding Ran
ran on a synthesized input
marcellacornia/mlnet/utilities.py
code served (permissive licence) · get_code("121a62c5927bf496")
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 (480, 640, 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

# Create a small test image with shape (240, 320, 3)
# This is smaller than the default padding dimensions
test_img = np.random.randint(0, 256, size=(240, 320, 3), dtype=np.uint8)

ARGS = {
    'img': test_img,
    'shape_r': 480,
    'shape_c': 640,
    '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 (480, 640, 3) — shape (480, 640, 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
preprocess_images Ran
ran on a synthesized input
marcellacornia/mlnet/utilities.py
code served (permissive licence) · get_code("70150474499bfa2e")
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 4, dtype family float, shape (2, 3, 480, 640) 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 temporary image files for testing
temp_dir = tempfile.mkdtemp()

# Create a simple test image and save it
def create_test_image(path, height=200, width=300):
    # Create a simple RGB image
    img = np.random.randint(0, 255, (height, width, 3), dtype=np.uint8)
    cv2.imwrite(path, img)

# Create 2 test images
image_path_1 = os.path.join(temp_dir, "test_image_1.jpg")
image_path_2 = os.path.join(temp_dir, "test_image_2.jpg")

create_test_image(image_path_1, height=150, width=200)
create_test_image(image_path_2, height=300, width=250)

# Define ARGS for preprocess_images function
ARGS = {
    "paths": [image_path_1, image_path_2],
    "shape_r": 480,
    "shape_c": 640
}
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 4, dtype family float, shape (2, 3, 480, 640) — shape (2, 3, 480, 640) 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_maps Ran
ran on a synthesized input
marcellacornia/mlnet/utilities.py
code served (permissive licence) · get_code("3dc79ad9b4824fb9")
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 4, dtype family float, shape (2, 1, 480, 640) 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 temporary directory and dummy image files
tmpdir = tempfile.mkdtemp()

# Create 2 small dummy grayscale images and save them
for i in range(2):
    # Create a small grayscale image (100x150 pixels)
    img = np.random.randint(0, 256, (100, 150), dtype=np.uint8)
    path = os.path.join(tmpdir, f"map_{i}.png")
    cv2.imwrite(path, img)

# Get paths to the created images
paths = [os.path.join(tmpdir, f"map_{i}.png") for i in range(2)]

ARGS = {
    "paths": paths,
    "shape_r": 480,
    "shape_c": 640
}
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 4, dtype family float, shape (2, 1, 480, 640) — shape (2, 1, 480, 640) 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 Not yet run
unverified (harvested, no recorded run)
marcellacornia/mlnet/model.py
code served (permissive licence) · get_code("52375b788589b77b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

This paper presents a novel deep architecture for saliency prediction. Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last convolutional layer to predict saliency maps. We propose an architecture which, instead, combines features extracted at different levels of a Convolutional Neural Network (CNN). Our model is composed of three main blocks: a feature extraction CNN, a feature encoding network, that weights low and high level feature maps, and a prior learning network. We compare our solution with state of the art saliency models on two public benchmarks datasets. Results show that our model outperforms under all evaluation metrics on the SALICON dataset, which is currently the largest public dataset for saliency prediction, and achieves competitive results on the MIT300 benchmark.

For agents

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

get_harvested_code_for_paper("1609.01064")
get_code_for_paper("1609.01064")
have("1609.01064")

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

curl https://syntology.ai/api/ran/1609.01064.json

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

[![Syntology run record](https://syntology.ai/api/ran/1609.01064.svg)](https://syntology.ai/paper/1609.01064)

Connect an agent — have() is free.