SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.04256 · 2024

Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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, 1 violated it and 0 have no contract verdict; 1 failure 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/2404.04256.json · badge: /api/ran/2404.04256.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
zifuwan/sigma canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
flops_selective_scan_fn Ran
ran, honoured the contract we drafted
zifuwan/sigma/models/builder.py
pointer only (licence: MIT); the stored copy get_code serves, from chenxi52/SfMamba, is pointer only (licence: NONE) · get_code("9a3adc8e6de35ac1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from chenxi52/SfMamba, and GitHub detected no licence in that repository 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.

random_mirror Ran
ran, violated the contract we drafted
zifuwan/sigma/dataloader/dataloader.py
code served (permissive licence) · get_code("83ca13ec3eefbcd1")
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 4, 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 cv2
import random
import numpy as np

# Set random seed for reproducibility
random.seed(0)

# Create small test images as numpy arrays
# Using distinct dimensions to make shapes unambiguous: (height=4, width=3, channels=3)
rgb = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
gt = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
modal_x = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

ARGS = {
    'rgb': rgb,
    'gt': gt,
    'modal_x': modal_x,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 4, 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
random_scale Ran
ran; our contract draft was wrong, not the code
zifuwan/sigma/dataloader/dataloader.py
code served (permissive licence) · get_code("3e2c98e28bc11bd4")
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 cv2
import random
import numpy as np

random.seed(0)

# Create sample image arrays with distinct dimensions
# rgb: 3-channel image (height=100, width=80)
rgb = np.random.randint(0, 256, (100, 80, 3), dtype=np.uint8)

# gt: 1-channel ground truth (height=100, width=80)
gt = np.random.randint(0, 10, (100, 80), dtype=np.uint8)

# modal_x: 3-channel modal image (height=100, width=80)
modal_x = np.random.randint(0, 256, (100, 80, 3), dtype=np.uint8)

# scales: list of scale factors to randomly choose from
scales = [0.5, 0.75, 1.0, 1.25]

ARGS = {
    "rgb": rgb,
    "gt": gt,
    "modal_x": modal_x,
    "scales": scales
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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
selective_scan_flop_jit Not yet run
unverified (harvested, no recorded run)
zifuwan/sigma/models/builder.py
code served (permissive licence) · get_code("1a7a2a1b97877257")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 2 later) and 0 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
flops_selective_scan_fn 12 other papers
3 dated earlier, 2 the same month, 7 later
2401.10166 (2024-01)
VMamba: Visual State Space Model
2402.15648 (2024-02)
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
2403.17839 (2024-03)
ReMamber: Referring Image Segmentation with Mamba Twister
and 9 more not named here
random_mirror 2 other papers
1 dated earlier, 1 same year, order not determinable
2203.04838 (2022-03)
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
random_scale 2 other papers
1 dated earlier, 1 same year, order not determinable
2203.04838 (2022-03)
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
selective_scan_flop_jit 2 other papers
2 later
2408.02615 (2024-08)
LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba
Fu_SegMAN_Omni-scale_Context_Modeling_with_State_Space_Models_and_Local_CVPR_2025_paper (2025 (year only))
SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation

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

Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environments. Leveraging additional modalities (X-modality) like thermal and depth alongside traditional RGB provides complementary information, enabling more robust and reliable prediction. In this work, we introduce Sigma, a Siamese Mamba network for multi-modal semantic segmentation utilizing the advanced Mamba. Unlike conventional methods that rely on CNNs, with their limited local receptive fields, or Vision Transformers (ViTs), which offer global receptive fields at the cost of quadratic complexity, our model achieves global receptive fields with linear complexity. By employing a Siamese encoder and innovating a Mamba-based fusion mechanism, we effectively select essential information from different modalities. A decoder is then developed to enhance the channel-wise modeling ability of the model. Our proposed method is rigorously evaluated on both RGB-Thermal and RGB-Depth semantic segmentation tasks, demonstrating its superiority and marking the first successful application of State Space Models (SSMs) in multi-modal perception tasks. Code is available at https://github.com/zifuwan/Sigma.

For agents

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

get_harvested_code_for_paper("2404.04256")
get_code_for_paper("2404.04256")
have("2404.04256")

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

curl https://syntology.ai/api/ran/2404.04256.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.04256.svg)](https://syntology.ai/paper/2404.04256)

Connect an agent — have() is free.