SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.03546 · ICLR · 2022

Language-driven Semantic Segmentation

Vladlen Koltun, Kilian Weinberger, Serge Belongie, Boyi Li, René Ranftl

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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; 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/2201.03546.json · badge: /api/ran/2201.03546.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
isl-org/lang-seg canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
krrish94/lseg-minimal reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_new_mask_pallete Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
isl-org/lang-seg/lseg_app.py
code served (permissive licence) · get_code("cd8fd543b1b4b1fe")
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. 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
import matplotlib.patches as mpatches

# Create a small numpy array for the mask image
# Shape: (1, 4, 5) - batch dimension, height, width
npimg = np.array([[[0, 1, 2, 1, 0],
                   [1, 2, 0, 2, 1],
                   [2, 0, 1, 0, 2],
                   [0, 1, 2, 1, 0]]], dtype=np.uint8)

# Create a palette with 256 colors * 3 channels (RGB)
# Each color is represented by 3 consecutive values (R, G, B)
new_palette = []
for i in range(256):
    new_palette.extend([i % 256, (i * 2) % 256, (i * 3) % 256])
new_palette = new_palette[:768]  # Ensure exactly 768 values (256 colors * 3)

# Create labels for the unique indices in the mask
labels = {i: f"class_{i}" for i in range(256)}

ARGS = {
    "npimg": npimg,
    "new_palette": new_palette,
    "out_label_flag": True,
    "labels": labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, matplotlib, 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
get_new_pallete Ran
ran, honoured the contract we drafted
krrish94/lseg-minimal/examples/lseg_openset_seg.py
pointer only (licence: NONE) · get_code("9803abda3688453c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, krrish94/lseg-minimal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_new_pallete Ran
ran, honoured the contract we drafted
isl-org/lang-seg/lseg_app.py
code served (permissive licence) · get_code("0fc141584bd295d9")
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 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.

# Setup code for get_new_pallete function

ARGS = {
    "num_cls": 5
}
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 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

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, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 1 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
get_new_mask_pallete 2 other papers
2 later
2403.11131 (2024-03)
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
2404.03658 (2024-04)
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
get_new_pallete 2 other papers
2 later
2403.11131 (2024-03)
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
2404.03658 (2024-04)
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "building") together with a transformer-based image encoder that computes dense per-pixel embeddings of the input image. The image encoder is trained with a contrastive objective to align pixel embeddings to the text embedding of the corresponding semantic class. The text embeddings provide a flexible label representation in which semantically similar labels map to similar regions in the embedding space (e.g., "cat" and "furry"). This allows LSeg to generalize to previously unseen categories at test time, without retraining or even requiring a single additional training sample. We demonstrate that our approach achieves highly competitive zero-shot performance compared to existing zero-and few-shot semantic segmentation methods, and even matches the accuracy of traditional segmentation algorithms when a fixed label set is provided. Code and demo are available at https://github.com/isl-org/lang-seg.

For agents

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

get_harvested_code_for_paper("2201.03546")
get_code_for_paper("2201.03546")
have("2201.03546")

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

curl https://syntology.ai/api/ran/2201.03546.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.03546.svg)](https://syntology.ai/paper/2201.03546)

Connect an agent — have() is free.