SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.12469 · 2023

Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 0 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/2308.12469.json · badge: /api/ran/2308.12469.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
google/diffseg canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
find_edges Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
google/diffseg/diffseg/utils.py
code served (permissive licence) · get_code("023a352094863b2c")
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, 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 numpy as np

# The function find_edges expects a numpy array M of shape (512, 512)
# It performs edge detection by comparing neighboring pixels
# and returns coordinates where edges are found

# Create a simple 512x512 array with some distinct regions to create edges
M = np.zeros((512, 512), dtype=int)
# Add a rectangular region with different values to create edges
M[100:300, 150:400] = 1
# Add another region to create more edges
M[350:450, 50:200] = 2

ARGS = {
    "M": M
}
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, ndim 2, dtype family float — a tuple 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
hungarian_matching Ran
ran; our contract draft was wrong, not the code
google/diffseg/diffseg/utils.py
code served (permissive licence) · get_code("7c271596415d695e")
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

np.random.seed(0)

# Small batch of predictions and labels
# pred: shape (batch_size, height, width) with class indices
# label: shape (batch_size, height, width) with class indices
batch_size = 2
height = 4
width = 3
n_class = 5

pred = np.random.randint(0, n_class, size=(batch_size, height, width))
label = np.random.randint(0, n_class, size=(batch_size, height, width))

ARGS = {
    "pred": pred,
    "label": label,
    "n_class": n_class
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
process_image Ran
ran, honoured the contract we drafted
google/diffseg/diffseg/utils.py
code served (permissive licence) · get_code("145bd246f65e64ca")
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 EagerTensor, ndim 3, dtype family float, shape (512, 512, 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 tempfile
import os
import numpy as np
import PIL.Image

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
image_array = np.random.randint(0, 256, (100, 80, 3), dtype=np.uint8)
image_path = os.path.join(temp_dir, "test_image.png")
pil_image = PIL.Image.fromarray(image_array)
pil_image.save(image_path)

ARGS = {
    "image_path": image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (512, 512, 3) — shape (512, 512, 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

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

Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent concepts of objects within its attention layers. Specifically, we introduce a simple yet effective iterative merging process based on measuring KL divergence among attention maps to merge them into valid segmentation masks. The proposed method does not require any training or language dependency to extract quality segmentation for any images. On COCO-Stuff-27, our method surpasses the prior unsupervised zero-shot SOTA method by an absolute 26% in pixel accuracy and 17% in mean IoU. The project page is at \url{https://sites.google.com/view/diffseg/home}.

For agents

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

get_harvested_code_for_paper("2308.12469")
get_code_for_paper("2308.12469")
have("2308.12469")

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

curl https://syntology.ai/api/ran/2308.12469.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.12469.svg)](https://syntology.ai/paper/2308.12469)

Connect an agent — have() is free.