SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.01599 · ECCV · 2022

DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation

Xiaojuan Qi, Jihan Yang, Runyu Ding, Jiang Li

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 1 has 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/2204.01599.json · badge: /api/ran/2204.01599.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
CVMI-Lab/DODA community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
DSNorm Ran
ran on a synthesized input
CVMI-Lab/DODA/model/dsnorm.py
code served (permissive licence) · get_code("50ba08851a41d2b2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn.modules.module import Module
from torch.nn.parameter import Parameter
import itertools

class DSNorm(Module):

    def __init__(self, num_features, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True):
        super(DSNorm, self).__init__()
        self.num_features = num_features
        self.eps = eps
        self.momentum = momentum
        self.affine = affine
        self.track_running_stats = track_running_stats
        self.domain_label = 0
        if self.affine:
            self.weight = Parameter(torch.Tensor(num_features))
            self.bias = Parameter(torch.Tensor(num_features))
        else:
            self.register_parameter('weight', None)
            self.register_parameter('bias', None)
        if self.track_running_stats:
            self.register_buffer('running_mean_source', torch.zeros(num_features))
            self.register_buffer('running_mean_target', torch.zeros(num_features))
            self.register_buffer('running_var_source', torch.ones(num_features))
            self.register_buffer('running_var_target', torch.ones(num_features))
            self.register_buffer('num_batches_tracked', torch.tensor(0, dtype=torch.long))
        else:
            self.register_parameter('running_mean_source', None)
            self.register_parameter('running_mean_target', None)
            self.register_parameter('running_var_source', None)
            self.register_parameter('running_var_target', None)
        self.reset_parameters()

    def reset_running_stats(self):
        if self.track_running_stats:
            self.running_mean_source.zero_()
            self.running_var_source.fill_(1)
            self.running_mean_target.zero_()
            self.running_var_target.fill_(1)
            self.num_batches_tracked.zero_()

    def set_domain_label(self, domain_label):
        self.domain_label = domain_label

    def reset_parameters(self):
        self.reset_running_stats()
        if self.affine:
            nn.init.ones_(self.weight)
            nn.init.zeros_(self.bias)

    def _check_input_dim(self, input):
        return NotImplemented

    def forward(self, input):
        self._check_input_dim(input)
        if self.momentum is None:
            exponential_average_factor = 0.0
        else:
            exponential_average_factor = self.momentum
        if self.training and self.track_running_stats:
            if self.num_batches_tracked is not None:
                self.num_batches_tracked += 1
                if self.momentum is None:
                    exponential_average_factor = 1.0 / float(self.num_batches_tracked)
                else:
                    exponential_average_factor = self.momentum
        return F.batch_norm(input, self.running_mean_target if self.domain_label else self.running_mean_source, self.running_var_target if self.domain_label else self.running_var_source, self.weight, self.bias, self.training or not self.track_running_stats, exponential_average_factor, self.eps)

    def extra_repr(self):
        return '{num_features}, eps={eps}, momentum={momentum}, affine={affine}, track_running_stats={track_running_stats}'.format(**self.__dict__)

    def _load_from_state_dict(self, state_dict, prefix, metadata, strict, missing_keys, unexpected_keys, error_msgs):
        version = metadata.get('version', None)
        if (version is None or version < 2) and self.track_running_stats:
            num_batches_tracked_key = prefix + 'num_batches_tracked'
            if num_batches_tracked_key not in state_dict:
                state_dict[num_batches_tracked_key] = torch.tensor(0, dtype=torch.long)
        self._load_from_state_dict_ds(state_dict, prefix, metadata, strict, missing_keys, unexpected_keys, error_msgs)

    def _load_from_state_dict_ds(self, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs):
        pass


INIT_ARGS = {
    'num_features': 4,
    'eps': 1e-05,
    'momentum': 0.1,
    'affine': True,
    'track_running_stats': True
}

ARGS = {
    'input': torch.randn(2, 4)
}

if __name__ == '__main__':
    dsnorm = DSNorm(**INIT_ARGS)
    dsnorm.train()
    output = dsnorm(**ARGS)
    print("Output shape:", output.shape)
    print("Output:", output)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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.

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

Deep learning approaches achieve prominent success in 3D semantic segmentation. However, collecting densely annotated real-world 3D datasets is extremely time-consuming and expensive. Training models on synthetic data and generalizing on real-world scenarios becomes an appealing alternative, but unfortunately suffers from notorious domain shifts. In this work, we propose a Data-Oriented Domain Adaptation (DODA) framework to mitigate pattern and context gaps caused by different sensing mechanisms and layout placements across domains. Our DODA encompasses virtual scan simulation to imitate real-world point cloud patterns and tail-aware cuboid mixing to alleviate the interior context gap with a cuboid-based intermediate domain. The first unsupervised sim-to-real adaptation benchmark on 3D indoor semantic segmentation is also built on 3D-FRONT, ScanNet and S3DIS along with 8 popular Unsupervised Domain Adaptation (UDA) methods. Our DODA surpasses existing UDA approaches by over 13% on both 3D-FRONT → ScanNet and 3D-FRONT → S3DIS. Code is available at https://github.com/CVMI-Lab/DODA.

For agents

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

get_harvested_code_for_paper("2204.01599")
get_code_for_paper("2204.01599")
have("2204.01599")

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

curl https://syntology.ai/api/ran/2204.01599.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.01599.svg)](https://syntology.ai/paper/2204.01599)

Connect an agent — have() is free.