SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.04538 · 2024

PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers

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/2407.04538.json · badge: /api/ran/2407.04538.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
ananthu-aniraj/pdiscoformer canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_dimensions Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ananthu-aniraj/pdiscoformer/utils/data_utils/dataset_utils.py
code served (permissive licence) · get_code("2255405dfa5c835b")
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) and returned tuple, 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
from PIL import Image

torch.manual_seed(0)

# Create a small tensor with shape (batch, height, width)
tensor_image = torch.randn(2, 4, 3)

# Create a small numpy array with shape (height, width, channels)
numpy_image = np.random.randn(4, 3, 3).astype(np.uint8)

# Create a small PIL Image
pil_image = Image.new('RGB', (3, 4))

ARGS = {
    'image': tensor_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — 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
load_json Ran
ran; our contract draft was wrong, not the code
ananthu-aniraj/pdiscoformer/utils/data_utils/dataset_utils.py
code served (permissive licence) · get_code("cea473d993ab7c54")
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) and returned dict. 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 json
import tempfile
import os

# Create a temporary JSON file with sample data
temp_dir = tempfile.mkdtemp()
json_path = os.path.join(temp_dir, "test_data.json")

sample_data = {
    "name": "test",
    "values": [1, 2, 3],
    "nested": {"key": "value"}
}

with open(json_path, 'w') as f:
    json.dump(sample_data, f)

ARGS = {
    "path": json_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
pil_loader Ran
ran, honoured the contract we drafted
ananthu-aniraj/pdiscoformer/utils/data_utils/dataset_utils.py
code served (permissive licence) · get_code("6df2bbbda7469611")
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) and returned Image. 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 tempfile
import os
from PIL import Image

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

# Create a simple RGB image and save it
test_img = Image.new('RGB', (10, 10), color=(255, 0, 0))
test_img.save(test_image_path)

ARGS = {
    'path': test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 2 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
pil_loader 66 other papers
52 dated earlier, 1 the same month, 11 later, 2 same year, order not determinable
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
and 63 more not named here

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

Computer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models. Existing approaches that perform part discovery driven by a fine-grained classification task make very restrictive assumptions on the geometric properties of the discovered parts; they should be small and compact. Although this prior is useful in some cases, in this paper we show that pre-trained transformer-based vision models, such as self-supervised DINOv2 ViT, enable the relaxation of these constraints. In particular, we find that a total variation (TV) prior, which allows for multiple connected components of any size, substantially outperforms previous work. We test our approach on three fine-grained classification benchmarks: CUB, PartImageNet and Oxford Flowers, and compare our results to previously published methods as well as a re-implementation of the state-of-the-art method PDiscoNet with a transformer-based backbone. We consistently obtain substantial improvements across the board, both on part discovery metrics and the downstream classification task, showing that the strong inductive biases in self-supervised ViT models require to rethink the geometric priors that can be used for unsupervised part discovery.

For agents

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

get_harvested_code_for_paper("2407.04538")
get_code_for_paper("2407.04538")
have("2407.04538")

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

curl https://syntology.ai/api/ran/2407.04538.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.04538.svg)](https://syntology.ai/paper/2407.04538)

Connect an agent — have() is free.