SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.14949 · 2023

Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 3 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/2309.14949.json · badge: /api/ran/2309.14949.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
gorilla-lab-scut/tribe canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
FunctionStatusWhere it lives
cf_learning_rate Ran
ran, honoured the contract we drafted
gorilla-lab-scut/tribe/train_for_petal_cifar10.py
pointer only (licence: NONE) · get_code("b128b1b1c37a4fe0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

entropy_energy Ran
ran; our contract draft was wrong, not the code
gorilla-lab-scut/tribe/core/adapter/lame.py
pointer only (licence: NONE) · get_code("340d65079d8e40ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

load_cifar100_train Ran
ran; our contract draft was wrong, not the code
gorilla-lab-scut/tribe/train_for_petal_cifar100.py
pointer only (licence: NONE) · get_code("75bf7879dc84bb70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

load_cifar10_train Ran
ran; our contract draft was wrong, not the code
gorilla-lab-scut/tribe/train_for_petal_cifar10.py
pointer only (licence: NONE) · get_code("c90018f7dd3ef01a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

softmax_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gorilla-lab-scut/tribe/core/adapter/base_adapter.py
pointer only (licence: NONE); the stored copy get_code serves, from hthieu166/petta, is pointer only (licence: NONE) · get_code("8cc4004512e3fa2f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

softmax_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gorilla-lab-scut/tribe/core/adapter/cotta.py
pointer only (licence: NONE) · get_code("e589e47d748af885")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

train Ran
ran, honoured the contract we drafted
gorilla-lab-scut/tribe/train_mnist.py
pointer only (licence: NONE) · get_code("bfba965ef40453f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

update_ema_variables Ran
ran; our contract draft was wrong, not the code
gorilla-lab-scut/tribe/core/adapter/cotta.py
pointer only (licence: NONE); the stored copy get_code serves, from joe817/gcal, is pointer only (licence: NONE) · get_code("a77d556c0aea19c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

update_model_probs Ran
ran; our contract draft was wrong, not the code
gorilla-lab-scut/tribe/core/adapter/eata.py
pointer only (licence: NONE) · get_code("f4a71b97346fb88d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

val Ran
ran, honoured the contract we drafted
gorilla-lab-scut/tribe/train_mnist.py
pointer only (licence: NONE) · get_code("f787337c5aaa6127")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

forward_and_adapt_eata Not yet run
unverified (harvested, no recorded run)
gorilla-lab-scut/tribe/core/adapter/eata.py
pointer only (licence: NONE) · get_code("7853dec9689a762f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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_tta_transforms Not yet run
unverified (harvested, no recorded run)
gorilla-lab-scut/tribe/core/adapter/cotta.py
pointer only (licence: NONE) · get_code("3dc11f35b4b01ab2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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.

laplacian_optimization Not yet run
unverified (harvested, no recorded run)
gorilla-lab-scut/tribe/core/adapter/lame.py
pointer only (licence: NONE) · get_code("47e54051e894c2e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorilla-lab-scut/tribe 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 4 later) and 7 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
update_ema_variables 14 other papers
3 dated earlier, 11 later · 2 only as an assembly brick
2203.13591 (2022-03)
Continual Test-Time Domain Adaptation
2212.09713 (2022-12)
A Probabilistic Framework for Lifelong Test-Time Adaptation
2306.04344 (2023-06)
ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
and 11 more not named here
softmax_entropy 8 other papers
2 dated earlier, 6 later · 2 only as an assembly brick
2303.13899 (2023-03)
Robust Test-Time Adaptation in Dynamic Scenarios
2306.04344 (2023-06)
ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
2311.18193 (2023-11)
Persistent Test-time Adaptation in Recurring Testing Scenarios
and 5 more not named here
update_model_probs 8 other papers
1 dated earlier, 6 later, 1 undated
2204.02610 (2022-04)
Efficient Test-Time Model Adaptation without Forgetting
2311.14402 (2023-11)
TEA: Test-time Energy Adaptation
2402.17316 (2024-02)
Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
and 5 more not named here
entropy_energy 5 other papers
1 dated earlier, 4 later
2308.10297 (2023-08)
DomainAdaptor: A Novel Approach to Test-time Adaptation
2401.08328 (2024-01)
Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
2405.00754 (2024-05)
CLIPArTT: Adaptation of CLIP to New Domains at Test Time
and 2 more not named here
laplacian_optimization 1 other paper
1 dated earlier
2308.10297 (2023-08)
DomainAdaptor: A Novel Approach to Test-time 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

Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions. However, these attempts may fail under more challenging real-world scenarios. Existing works mainly consider real-world test-time adaptation under non-i.i.d. data stream and continual domain shift. In this work, we first complement the existing real-world TTA protocol with a globally class imbalanced testing set. We demonstrate that combining all settings together poses new challenges to existing methods. We argue the failure of state-of-the-art methods is first caused by indiscriminately adapting normalization layers to imbalanced testing data. To remedy this shortcoming, we propose a balanced batchnorm layer to swap out the regular batchnorm at inference stage. The new batchnorm layer is capable of adapting without biasing towards majority classes. We are further inspired by the success of self-training (ST) in learning from unlabeled data and adapt ST for test-time adaptation. However, ST alone is prone to over adaption which is responsible for the poor performance under continual domain shift. Hence, we propose to improve self-training under continual domain shift by regularizing model updates with an anchored loss. The final TTA model, termed as TRIBE, is built upon a tri-net architecture with balanced batchnorm layers. We evaluate TRIBE on four datasets representing real-world TTA settings. TRIBE consistently achieves the state-of-the-art performance across multiple evaluation protocols. The code is available at https://github.com/Gorilla-Lab-SCUT/TRIBE.

For agents

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

get_harvested_code_for_paper("2309.14949")
get_code_for_paper("2309.14949")
have("2309.14949")

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

curl https://syntology.ai/api/ran/2309.14949.json

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

[![Syntology run record](https://syntology.ai/api/ran/2309.14949.svg)](https://syntology.ai/paper/2309.14949)

Connect an agent — have() is free.