SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1703.08710 · 2017

Count-ception: Counting by Fully Convolutional Redundant Counting

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 0 have no contract verdict; 2 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/1703.08710.json · badge: /api/ran/1703.08710.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
roggirg/count-ception_mbm community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
getCellCountCells Ran
ran; our contract draft was wrong, not the code
roggirg/count-ception_mbm/utils/create_datafiles.py
code served (permissive licence) · get_code("30431ec96b0a7625")
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 1, dtype family int; 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 numpy as np

torch.manual_seed(0)

# Create a small 2D numpy array to represent markers
# The function indexes into it with [y:y+h, x:x+w] and checks where values == 1
markers = np.array([
    [0, 1, 0, 1, 0],
    [1, 1, 0, 0, 1],
    [0, 0, 1, 1, 0],
    [1, 0, 1, 0, 1],
    [0, 1, 0, 1, 1]
], dtype=np.int32)

# xyhw: x, y, h, w coordinates for a bounding box
# x=1, y=1 is the top-left corner, h=3, w=2 is height and width
xyhw = (1, 1, 3, 2)

ARGS = {
    "markers": markers,
    "xyhw": xyhw
}
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 list, ndim 1, dtype family int — 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
getLabelsCells Ran
ran; our contract draft was wrong, not the code
roggirg/count-ception_mbm/utils/create_datafiles.py
code served (permissive licence) · get_code("6cf29f2985b712d0")
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

# Analyze the function getLabelsCells to understand what it needs:
# - markers: 2D numpy array that supports slicing and == comparison, .sum()
# - img_pad: numpy array with .shape attribute
# - base_x, base_y: integers (not actually used in function body)
# - stride: integer used for division and iteration
# - patch_size: integer used for slicing
# - framesize_h, framesize_w: integers used for slicing

# Create small test data
np.random.seed(0)

# markers: 2D array where we check for == 1
# Make it small but large enough for the iterations
markers = np.random.randint(0, 2, size=(128, 128))
markers[10:20, 10:20] = 1  # Add some cells to count

# img_pad: used only for .shape[0] and .shape[1]
# We need height and width such that when divided by stride, we get reasonable dimensions
img_pad = np.zeros((96, 96))

# base_x, base_y: not used in function body, so arbitrary values
base_x = 0
base_y = 0

# stride: used in height = int(img_pad.shape[0] / stride) and width calculation
# and in iteration loops and getCellCountCells calls
stride = 8

# patch_size: used in getCellCountCells for slicing
patch_size = 32

# framesize_h, framesize_w: used in final getCellCountCells call
framesize_h = 96
framesize_w = 96

ARGS = {
    "markers": markers,
    "img_pad": img_pad,
    "base_x": base_x,
    "base_y": base_y,
    "stride": stride,
    "patch_size": patch_size,
    "framesize_h": framesize_h,
    "framesize_w": framesize_w,
}
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
getMarkersCells Not yet run
unverified (harvested, no recorded run)
roggirg/count-ception_mbm/utils/create_datafiles.py
code served (permissive licence) · get_code("3bf86e48b409ed20")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Counting objects in digital images is a process that should be replaced by machines. This tedious task is time consuming and prone to errors due to fatigue of human annotators. The goal is to have a system that takes as input an image and returns a count of the objects inside and justification for the prediction in the form of object localization. We repose a problem, originally posed by Lempitsky and Zisserman, to instead predict a count map which contains redundant counts based on the receptive field of a smaller regression network. The regression network predicts a count of the objects that exist inside this frame. By processing the image in a fully convolutional way each pixel is going to be accounted for some number of times, the number of windows which include it, which is the size of each window, (i.e., 32x32 = 1024). To recover the true count we take the average over the redundant predictions. Our contribution is redundant counting instead of predicting a density map in order to average over errors. We also propose a novel deep neural network architecture adapted from the Inception family of networks called the Count-ception network. Together our approach results in a 20% relative improvement (2.9 to 2.3 MAE) over the state of the art method by Xie, Noble, and Zisserman in 2016.

For agents

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

get_harvested_code_for_paper("1703.08710")
get_code_for_paper("1703.08710")
have("1703.08710")

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

curl https://syntology.ai/api/ran/1703.08710.json

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

[![Syntology run record](https://syntology.ai/api/ran/1703.08710.svg)](https://syntology.ai/paper/1703.08710)

Connect an agent — have() is free.