SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.21708 · NeurIPS · 2024

Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation

Bo Li, Pan Zhou, Hao Zhang, Yang Tang, Peng-Tao Jiang, Ruihao Xia, Yu Liang

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 2 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/2410.21708.json · badge: /api/ran/2410.21708.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
XiaRho/MADM canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
batched_input_to_device Ran
ran; our contract draft was wrong, not the code
XiaRho/MADM/modeling/preprocess.py
pointer only (licence: NONE) · get_code("69e60dbee942ddfa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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_grad_norm Ran
ran, honoured the contract we drafted
XiaRho/MADM/engine/train_loop.py
pointer only (licence: NONE) · get_code("c6bf0d68150e96b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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_model_from_module Ran
ran; our contract draft was wrong, not the code
XiaRho/MADM/engine/defaults.py
pointer only (licence: NONE) · get_code("b9e85d4f33e5f142")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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_optimizer_parameters Ran
ran; our contract draft was wrong, not the code
XiaRho/MADM/engine/train_loop.py
pointer only (licence: NONE) · get_code("e9eb46e7a17bab8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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.

group_by_prefix Ran
ran; our contract draft was wrong, not the code
XiaRho/MADM/checkpoint/odise_checkpointer.py
pointer only (licence: NONE) · get_code("b3e569142043c972")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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.

reduce_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
XiaRho/MADM/modeling/criterion.py
pointer only (licence: NONE); the stored copy get_code serves, from OpenFirework/pytorch_solov2, is pointer only (licence: NONE) · get_code("b2b9a1966482ef96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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.

weight_reduce_loss Ran
ran; our contract draft was wrong, not the code
XiaRho/MADM/modeling/criterion.py
pointer only (licence: NONE) · get_code("9a78b68ccf3be3bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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.

auto_scale_workers Not yet run
unverified (harvested, no recorded run)
XiaRho/MADM/config/utils.py
pointer only (licence: NONE) · get_code("208961850384d92d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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. No invocation recorded.

get_dataset_from_loader Not yet run
unverified (harvested, no recorded run)
XiaRho/MADM/engine/defaults.py
pointer only (licence: NONE) · get_code("ef1831a6bdc512e6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XiaRho/MADM 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. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 5 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
reduce_loss 18 other papers
15 dated earlier, 1 later, 2 same year, order not determinable
2003.10152 (2020-03)
SOLOv2: Dynamic and Fast Instance Segmentation
2003.10778 (2020-03)
PanNuke Dataset Extension, Insights and Baselines
2107.08430 (2021-07)
YOLOX: Exceeding YOLO Series in 2021
and 15 more not named here
batched_input_to_device 1 other paper
1 later
2411.13243 (2024-11)
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
group_by_prefix 1 other paper
1 later
2411.13243 (2024-11)
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
weight_reduce_loss 1 other paper
1 dated earlier
2112.11088 (2021-12)
EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection

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

Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation hinders their performance and restricts their application in real-world multimodal scenarios. To address this issue, we propose Modality Adaptation with text-toimage Diffusion Models (MADM) for semantic segmentation task which utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities. Specifically, MADM comprises two key complementary components to tackle major challenges. First, due to the large modality gap, using one modal data to generate pseudo labels for another modality suffers from a significant drop in accuracy. To address this, MADM designs diffusion-based pseudo-label generation which adds latent noise to stabilize pseudolabels and enhance label accuracy. Second, to overcome the limitations of latent low-resolution features in diffusion models, MADM introduces the label palette and latent regression which converts one-hot encoded labels into the RGB form by palette and regresses them in the latent space, thus ensuring the pre-trained decoder for up-sampling to obtain fine-grained features. Extensive experimental results demonstrate that MADM achieves state-of-the-art adaptation performance across various modality tasks, including images to depth, infrared, and event modalities. We open-source our code and models at https://github.com/XiaRho/MADM.

For agents

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

get_harvested_code_for_paper("2410.21708")
get_code_for_paper("2410.21708")
have("2410.21708")

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

curl https://syntology.ai/api/ran/2410.21708.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.21708.svg)](https://syntology.ai/paper/2410.21708)

Connect an agent — have() is free.