SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.03430 · 2023

ShareCMP: Polarization-Aware RGB-P Semantic Segmentation

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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 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/2312.03430.json · badge: /api/ran/2312.03430.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
lefteyex/sharecmp canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
aolp Ran
ran, honoured the contract we drafted
lefteyex/sharecmp/sharecmp/datasets/transforms/polarize_transforms.py
code served (permissive licence) · get_code("a3cb3187c64b006d")
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 ndarray, ndim 2, dtype family float, shape (2, 4) 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 numpy as np

# Create sample Stokes parameters as numpy arrays
# These represent polarization states, typically with shape (batch_size, ...)
s_0 = np.array([[1.0, 1.0, 1.0, 1.0],
                [1.0, 1.0, 1.0, 1.0]])

s_1 = np.array([[0.5, 0.3, 0.7, 0.2],
                [0.4, 0.6, 0.1, 0.8]])

s_2 = np.array([[0.3, 0.5, 0.2, 0.6],
                [0.2, 0.4, 0.5, 0.3]])

s_3 = np.array([[0.1, 0.2, 0.3, 0.1],
                [0.2, 0.1, 0.2, 0.4]])

eps = 1e-05

ARGS = {
    "s_0": s_0,
    "s_1": s_1,
    "s_2": s_2,
    "s_3": s_3,
    "eps": eps
}
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 ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
aolp_sin Ran
ran, honoured the contract we drafted
lefteyex/sharecmp/sharecmp/datasets/transforms/polarize_transforms.py
code served (permissive licence) · get_code("750534622f7ce5d3")
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 ndarray, ndim 2, dtype family float, shape (2, 4) 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 numpy as np

# Create small numpy arrays with distinct shapes for each parameter
# The function uses s_0, s_1, s_2, s_3 as Stokes parameters
# s_2 is divided by s_0, so they should have compatible shapes
# Using shape (2, 4) for variety

np.random.seed(0)

s_0 = np.random.rand(2, 4) + 0.5  # Add 0.5 to ensure non-zero values
s_1 = np.random.rand(2, 4)
s_2 = np.random.rand(2, 4)
s_3 = np.random.rand(2, 4)
eps = 1e-5

ARGS = {
    "s_0": s_0,
    "s_1": s_1,
    "s_2": s_2,
    "s_3": s_3,
    "eps": eps,
}
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 ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
stokes Ran
ran, honoured the contract we drafted
lefteyex/sharecmp/sharecmp/datasets/transforms/polarize_transforms.py
code served (permissive licence) · get_code("3509aaa8facb7a20")
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 3, 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

# Create small test images for polarization angles
# Shape: (2, 4) - batch of 2, spatial dimensions 4x1 (or 2x2)
img_0 = np.random.randint(0, 256, size=(2, 4), dtype=np.uint8)
img_45 = np.random.randint(0, 256, size=(2, 4), dtype=np.uint8)
img_90 = np.random.randint(0, 256, size=(2, 4), dtype=np.uint8)
img_135 = np.random.randint(0, 256, size=(2, 4), dtype=np.uint8)

ARGS = {
    "img_0": img_0,
    "img_45": img_45,
    "img_90": img_90,
    "img_135": img_135,
}
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 3, 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

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

Multimodal semantic segmentation is developing rapidly, but the modality of RGB-\textbf{P}olarization remains underexplored. To delve into this problem, we construct a UPLight RGB-P segmentation benchmark with 12 typical underwater semantic classes. In this work, we design the ShareCMP, an RGB-P semantic segmentation framework with a shared dual-branch architecture (ShareCMP Encoder), which reduces the parameters and memory space by about 33.8\% compared to previous dual-branch models. It encompasses a Polarization Generate Attention (PGA) module designed to generate polarization modal images with richer polarization properties for the encoder. In addition, we introduce the Class Polarization-Aware Loss (CPALoss) with Class Polarization-Aware Auxiliary Head (CPAAHead) to improve the learning and understanding of the encoder for polarization modal information and to optimize the PGA module. With extensive experiments on a total of three RGB-P benchmarks, our ShareCMP achieves the best performance in mIoU with fewer parameters on the UPLight (92.45{\small (+0.32)}\%), ZJU (92.7{\small (+0.1)}\%), and MCubeS (50.99{\small (+1.51)}\%) datasets. And our ShareCMP (w/o PGA) achieves competitive or even higher performance on other RGB-X datasets compared to the corresponding state-of-the-art RGB-X methods. The code and datasets are available at https://github.com/LEFTeyex/ShareCMP.

For agents

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

get_harvested_code_for_paper("2312.03430")
get_code_for_paper("2312.03430")
have("2312.03430")

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

curl https://syntology.ai/api/ran/2312.03430.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.03430.svg)](https://syntology.ai/paper/2312.03430)

Connect an agent — have() is free.