SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.01480 · CVPR · 2023

Delivering Arbitrary-Modal Semantic Segmentation

Kunyu Peng, Jiaming Zhang, Kailun Yang, Rainer Stiefelhagen, Ruiping Liu, Hao Shi, Simon Reiß, Kaiwei Wang, Haodong Fu

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 0 have no contract verdict; 7 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/2303.01480.json · badge: /api/ran/2303.01480.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
jamycheung/DELIVER canonical (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
FunctionStatusWhere it lives
get_loss Ran
ran; our contract draft was wrong, not the code
jamycheung/DELIVER/semseg/losses.py
code served (permissive licence) · get_code("3029c24a500aea0e")
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 Dice. 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
from torch import nn, Tensor

torch.manual_seed(0)

ARGS = {
    'loss_fn_name': 'Dice',
    'ignore_label': 255,
    'cls_weights': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Dice — a Dice output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Dice 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
get_optimizer Ran
ran; our contract draft was wrong, not the code
jamycheung/DELIVER/semseg/optimizers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ruipingl/miss, is pointer only (licence: NONE) · get_code("624e13fbf125c2a5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ruipingl/miss, 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.

get_scheduler Ran
ran; our contract draft was wrong, not the code
jamycheung/DELIVER/semseg/schedulers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ruipingl/miss, is pointer only (licence: NONE) · get_code("1190c7468e2cdaa7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ruipingl/miss, 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.

get_train_augmentation Ran
ran; our contract draft was wrong, not the code
jamycheung/DELIVER/semseg/augmentations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ruipingl/miss, is pointer only (licence: NONE) · get_code("36844e88d38a0881")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ruipingl/miss, 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.

get_train_augmentation Ran
ran; our contract draft was wrong, not the code
jamycheung/DELIVER/semseg/augmentations_mm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ruipingl/miss, is pointer only (licence: NONE) · get_code("1ce37e1fa8008660")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ruipingl/miss, 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.

get_val_augmentation Ran
ran; our contract draft was wrong, not the code
jamycheung/DELIVER/semseg/augmentations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ruipingl/miss, is pointer only (licence: NONE) · get_code("c63b165d09644f24")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ruipingl/miss, 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.

get_val_augmentation Ran
ran; our contract draft was wrong, not the code
jamycheung/DELIVER/semseg/augmentations_mm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ruipingl/miss, is pointer only (licence: NONE) · get_code("1096caea85dc06d3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ruipingl/miss, 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.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 6 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
get_loss 1 other paper
1 later
ijcai2025_0179 (2025 (year only))
Squeezing Context into Patches: Towards Memory-Efficient Ultra-High Resolution Semantic Segmentation
get_optimizer 1 other paper
1 later
2401.16923 (2024-01)
Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
get_scheduler 1 other paper
1 later
2401.16923 (2024-01)
Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
get_train_augmentation 1 other paper
1 later
2401.16923 (2024-01)
Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
get_train_augmentation 1 other paper
1 later
2401.16923 (2024-01)
Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
get_val_augmentation 1 other paper
1 later
2401.16923 (2024-01)
Fourier Prompt Tuning for Modality-Incomplete Scene 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

Multimodal fusion can make semantic segmentation more robust. However, fusing an arbitrary number of modalities remains underexplored. To delve into this problem, we create the DELIVER arbitrary-modal segmentation benchmark, covering Depth, LiDAR, multiple Views, Events, and RGB. Aside from this, we provide this dataset in four severe weather conditions as well as five sensor failure cases to exploit modal complementarity and resolve partial outages. To make this possible, we present the arbitrary cross-modal segmentation model CMNEXT. It encompasses a Self-Query Hub (SQ-Hub) designed to extract effective information from any modality for subsequent fusion with the RGB representation and adds only negligible amounts of parameters (∼0.01M ) per additional modality. On top, to efficiently and flexibly harvest discriminative cues from the auxiliary modalities, we introduce the simple Parallel Pooling Mixer (PPX). With extensive experiments on a total of six benchmarks, our CMNEXT achieves state-of-the-art performance on the DELIVER, KITTI-360, MFNet, NYU Depth V2, UrbanLF, and MCubeS datasets, allowing to scale from 1 to 81 modalities. On the freshly collected DELIVER, the quad-modal CMNEXT reaches up to 66.30% in mIoU with a +9.10% gain as compared to the mono-modal baseline. 1

For agents

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

get_harvested_code_for_paper("2303.01480")
get_code_for_paper("2303.01480")
have("2303.01480")

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

curl https://syntology.ai/api/ran/2303.01480.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.01480.svg)](https://syntology.ai/paper/2303.01480)

Connect an agent — have() is free.