SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.11228 · 2022

NamedMask: Distilling Segmenters from Complementary Foundation Models

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 2 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/2209.11228.json · badge: /api/ran/2209.11228.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
noelshin/namedmask canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
convert_p_image_to_p_pseudo_mask Ran
ran on a synthesized input
noelshin/namedmask/datasets/imagenet.py
code served (permissive licence) · get_code("31107409fcce10d3")
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 str. 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 numpy as np
from typing import Dict, List, Optional, Tuple, Union

# Analyze the function to understand what arguments are needed
# The function takes:
# - dir_dataset: str - a directory path
# - p_image: str - a path to an image that will be split by '/'
# - use_expert_pseudo_masks: bool - flag to determine which path to use
# - eval_dataset_name: Optional[str] - dataset name, required if use_expert_pseudo_masks is True

# The function expects p_image to have at least 3 path components separated by '/'
# It extracts: split, wnid, filename = p_image.split('/')[-3:]

ARGS = {
    'dir_dataset': '/path/to/dataset',
    'p_image': 'train/n01440764/image_001.JPEG',
    'use_expert_pseudo_masks': False,
    'eval_dataset_name': None
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
convert_p_image_to_p_pseudo_mask Ran
ran on a synthesized input
noelshin/namedmask/expert_inference.py
code served (permissive licence) · get_code("558e1f41981ec4b1")
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 str. 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.

# The function parses a file path, extracts components, and constructs a new path
# It takes three string parameters and returns a string

# Construct arguments that would work with the function logic
eval_dataset_name = "imagenet_subset"
dir_dataset = "/data/datasets"
p_image = "train/n01440764/n01440764_10.JPEG"

ARGS = {
    "eval_dataset_name": eval_dataset_name,
    "dir_dataset": dir_dataset,
    "p_image": p_image,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
convert_to_separable_conv Not yet run
unverified (harvested, no recorded run)
noelshin/namedmask/networks/deeplab/_deeplab.py
code served (permissive licence) · get_code("ce942a958c0ae909")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 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
convert_to_separable_conv 10 other papers
7 dated earlier, 3 later
1706.05587 (2017-06)
Rethinking Atrous Convolution for Semantic Image Segmentation
1905.03561 (2019-05)
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
2007.07984 (2020-07)
Leveraging Category Information for Single-Frame Visual Sound Source Separation
and 7 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

The goal of this work is to segment and name regions of images without access to pixel-level labels during training. To tackle this task, we construct segmenters by distilling the complementary strengths of two foundation models. The first, CLIP (Radford et al. 2021), exhibits the ability to assign names to image content but lacks an accessible representation of object structure. The second, DINO (Caron et al. 2021), captures the spatial extent of objects but has no knowledge of object names. Our method, termed NamedMask, begins by using CLIP to construct category-specific archives of images. These images are pseudo-labelled with a category-agnostic salient object detector bootstrapped from DINO, then refined by category-specific segmenters using the CLIP archive labels. Thanks to the high quality of the refined masks, we show that a standard segmentation architecture trained on these archives with appropriate data augmentation achieves impressive semantic segmentation abilities for both single-object and multi-object images. As a result, our proposed NamedMask performs favourably against a range of prior work on five benchmarks including the VOC2012, COCO and large-scale ImageNet-S datasets.

For agents

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

get_harvested_code_for_paper("2209.11228")
get_code_for_paper("2209.11228")
have("2209.11228")

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

curl https://syntology.ai/api/ran/2209.11228.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.11228.svg)](https://syntology.ai/paper/2209.11228)

Connect an agent — have() is free.