SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.10902 · CVPR · 2023

Feature Alignment and Uniformity for Test Time Adaptation

Rui Li, Shuai Wang, Jianguo Zhang, Daoan Zhang, Zipei Yan

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 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/2303.10902.json · badge: /api/ran/2303.10902.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
sakurajimamaiii/tsd marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
TSD Ran
ran on a synthesized input · constructed an object; no result was computed
sakurajimamaiii/tsd/code/adapt_algorithm.py
code served (permissive licence) · get_code("c4781897e57a47e8")
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 an instance of its own class, TSD: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Create a minimal featurizer (maps input to features)
class MinimalFeaturizer(nn.Module):
    def __init__(self, input_dim=4, feature_dim=4):
        super().__init__()
        self.fc = nn.Linear(input_dim, feature_dim)
    
    def forward(self, x):
        return self.fc(x)

# Create a minimal classifier with fc layer
class MinimalClassifier(nn.Module):
    def __init__(self, feature_dim=4, num_classes=3):
        super().__init__()
        self.fc = nn.Linear(feature_dim, num_classes)
    
    def forward(self, x):
        return self.fc(x)

# Create a minimal model that has featurizer and classifier
class MinimalModel(nn.Module):
    def __init__(self, input_dim=4, feature_dim=4, num_classes=3):
        super().__init__()
        self.featurizer = MinimalFeaturizer(input_dim, feature_dim)
        self.classifier = MinimalClassifier(feature_dim, num_classes)
    
    def forward(self, x):
        z = self.featurizer(x)
        p = self.classifier(z)
        return p

# Create model
model = MinimalModel(input_dim=4, feature_dim=4, num_classes=3)

# Create optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Build ARGS dict with all required parameters for TSD.__init__
ARGS = {
    'model': model,
    'optimizer': optimizer,
    'lam': 0.1,
    'filter_K': 100,
    'steps': 1,
    'episodic': False
}
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 TSD — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TSD 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
softmax_kl_loss Ran
ran; our contract draft was wrong, not the code
sakurajimamaiii/tsd/code/adapt_algorithm.py
code served (permissive licence) · get_code("cb16c4f968d3f225")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.functional as F

torch.manual_seed(0)

# Create small tensor arguments
# batch_size=2, num_classes=4
input_logits = torch.randn(2, 4)
target_logits = torch.randn(2, 4)

ARGS = {
    "input_logits": input_logits,
    "target_logits": target_logits,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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
topk_cluster Not yet run
unverified (harvested, no recorded run)
sakurajimamaiii/tsd/code/adapt_algorithm.py
code served (permissive licence) · get_code("e2750a91fb684b57")
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, 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 3 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

Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pre-trained models on the training domains. We first address TTA as a feature revision problem due to the domain gap between source domains and target domains. After that, we follow the two measurements alignment and uniformity to discuss the test time feature revision. For test time feature uniformity, we propose a test time self-distillation strategy to guarantee the consistency of uniformity between representations of the current batch and all the previous batches. For test time feature alignment, we propose a memorized spatial local clustering strategy to align the representations among the neighborhood samples for the upcoming batch. To deal with the common noisy label problem, we propound the entropy and consistency filters to select and drop the possible noisy labels. To prove the scalability and efficacy of our method, we conduct experiments on four domain generalization benchmarks and four medical image segmentation tasks with various backbones. Experiment results show that our method not only improves baseline stably but also outperforms existing state-of-the-art test time adaptation methods.

For agents

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

get_harvested_code_for_paper("2303.10902")
get_code_for_paper("2303.10902")
have("2303.10902")

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

curl https://syntology.ai/api/ran/2303.10902.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.10902.svg)](https://syntology.ai/paper/2303.10902)

Connect an agent — have() is free.