SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.07155 · CVPR · 2024

Unified Language-driven Zero-shot Domain Adaptation

Jiaya Jia, Li Jiang, Zhuotao Tian, Senqiao Yang

arXiv · PDF · Open in the Atlas

Code that ran

1 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 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/2404.07155.json · badge: /api/ran/2404.07155.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
Yangsenqiao/ULDA marked official in Papers with Code
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
_Segmentation Ran
ran on a synthesized input
Yangsenqiao/ULDA/network/modeling.py
code served (permissive licence) · get_code("3415d85a07599619")
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 tuple. 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 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

def calc_mean_std(feat, eps=1e-5):
    size = feat.size()
    N, C = size[:2]
    feat_var = feat.view(N, C, -1).var(dim=2) + eps
    feat_std = feat_var.sqrt().view(N, C, 1, 1)
    feat_mean = feat.view(N, C, -1).mean(dim=2).view(N, C, 1, 1)
    return feat_mean, feat_std

class MockBackbone(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
        self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
        self.relu = nn.ReLU()
        
    def forward(self, x, trunc1=False, trunc2=False, trunc3=False, trunc4=False,
                get1=False, get2=False, get3=False, get4=False, use_relu=True):
        if not trunc1:
            x = self.conv1(x)
            if use_relu:
                x = self.relu(x)
            if get1:
                return x
        
        x = self.conv2(x)
        if use_relu:
            x = self.relu(x)
        
        if get4:
            return x
        
        return x

class MockClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv_low = nn.Conv2d(16, 8, 1)
        self.conv_out = nn.Conv2d(32, 16, 1)
        self.final = nn.Conv2d(24, 5, 1)
        
    def forward(self, features):
        low = self.conv_low(features['low_level'])
        out = self.conv_out(features['out'])
        out_up = F.interpolate(out, size=low.shape[-2:], mode='bilinear', align_corners=False)
        combined = torch.cat([low, out_up], dim=1)
        return self.final(combined)

backbone = MockBackbone()
classifier = MockClassifier()

INIT_ARGS = {
    'backbone': backbone,
    'classifier': classifier
}

ARGS = {
    'x': torch.randn(2, 3, 16, 12),
    'mu_t_f1': 0,
    'std_t_f1': 0,
    'transfer': False,
    'mix': False,
    'activation': None
}
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 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
DeepLabV3 Not yet run
unverified (harvested, no recorded run)
Yangsenqiao/ULDA/network/modeling.py
code served (permissive licence) · get_code("bb85b8a40fee3b20")
How it ran

no invocation recorded.

deeplabv3plus_resnet_clip Not yet run
unverified (harvested, no recorded run)
Yangsenqiao/ULDA/network/modeling.py
code served (permissive licence) · get_code("e8f6210425ee91ae")
How it ran

no invocation recorded.

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
deeplabv3plus_resnet_clip
brick of this paper's assembly: entry
1 other paper
1 dated earlier
Fahes_PODA_Prompt-driven_Zero-shot_Domain_Adaptation_ICCV_2023_paper (2023 (year only))
PØDA: Prompt-driven Zero-shot Domain Adaptation

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

This paper introduces Unified Language-driven Zeroshot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge. We identify the constraints in the existing language-driven zero-shot domain adaptation task, particularly the requirement for domain IDs and domain-specific models, which may restrict flexibility and scalability. To overcome these issues, we propose a new framework for ULDA, consisting of Hierarchical Context Alignment (HCA), Domain Consistent Representation Learning (DCRL), and Text-Driven Rectifier (TDR). These components work synergistically to align simulated features with target text across multiple visual levels, retain semantic correlations between different regional representations, and rectify biases between simulated and real target visual features, respectively. Our extensive empirical evaluations demonstrate that this framework achieves competitive performance in both settings, surpassing even the model that requires domain-ID, showcasing its superiority and generalization ability. The proposed method is not only effective but also maintains practicality and efficiency, as it does not introduce additional computational costs during inference. The code is available on the project website 1 .

For agents

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

get_harvested_code_for_paper("2404.07155")
get_code_for_paper("2404.07155")
have("2404.07155")

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

curl https://syntology.ai/api/ran/2404.07155.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.07155.svg)](https://syntology.ai/paper/2404.07155)

Connect an agent — have() is free.