Papers › SoTTA: Robust Test-Time Adaptation on Noisy Data Streams

SoTTA: Robust Test-Time Adaptation on Noisy Data Streams

16 Oct 2023NeurIPS 2023 11arXiv:2310.10074archive 2025-07-28

Taesik Gong, Yewon Kim, Taeckyung Lee, Sorn Chottananurak, Sung-Ju Lee

Test-time adaptation (TTA) aims to address distributional shifts between training and testing data using only unlabeled test data streams for continual model adaptation. However, most TTA methods assume benign test streams, while test samples could be unexpectedly diverse in the wild. For instance, an unseen object or noise could appear in autonomous driving. This leads to a new threat to existing TTA algorithms; we found that prior TTA algorithms suffer from those noisy test samples as they blindly adapt to incoming samples. To address this problem, we present Screening-out Test-Time Adaptation (SoTTA), a novel TTA algorithm that is robust to noisy samples. The key enabler of SoTTA is two-fold: (i) input-wise robustness via high-confidence uniform-class sampling that effectively filters out the impact of noisy samples and (ii) parameter-wise robustness via entropy-sharpness minimization that improves the robustness of model parameters against large gradients from noisy samples. Our evaluation with standard TTA benchmarks with various noisy scenarios shows that our method outperforms state-of-the-art TTA methods under the presence of noisy samples and achieves comparable accuracy to those methods without noisy samples. The source code is available at https://github.com/taeckyung/SoTTA .

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.10074")

Code

Syntology Ran 8 of 13 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

taeckyung/SoTTA officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 8 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran · fixture could not drive it
5ran
5unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from taeckyung/SoTTA. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

CSTU taeckyung/SoTTA/learner/sotta.py official repository ran MIT (permissive) · 37954f9b076ab80e · report
ConfFIFO taeckyung/SoTTA/learner/sotta.py official repository ran MIT (permissive) · e8b803dc0956626a · report
FIFO taeckyung/SoTTA/learner/sotta.py official repository ran MIT (permissive) · e2796dd5351a82a0 · report
HLoss taeckyung/SoTTA/learner/sotta.py official repository ran fingerprinted MIT (permissive) · cb6c1ea449710403 · report
MemoryItem taeckyung/SoTTA/learner/sotta.py official repository ran MIT (permissive) · a829fc46b04e2042 · report
calc_energy taeckyung/SoTTA/learner/sotta.py official repository ran · fixture could not drive it MIT (permissive) · fc962c3df9bd26ac · report
sam_collect_params taeckyung/SoTTA/learner/sotta.py official repository ran · our draft was wrong MIT (permissive) · bde04657eba9f1f5 · report
softmax_entropy taeckyung/SoTTA/learner/sotta.py official repository ran · fixture could not drive it MIT (permissive) · a9edd84f4eedeec8 · report
DNN taeckyung/SoTTA/learner/sotta.py official repository unverified MIT (permissive) · d2cf21a1fafc8cca · report
HUS taeckyung/SoTTA/learner/sotta.py official repository unverified MIT (permissive) · 7c10fe54b79944cb · report
SoTTA taeckyung/SoTTA/learner/sotta.py official repository unverified MIT (permissive) · d02457bfc418d32b · report
load_cache taeckyung/SoTTA/learner/sotta.py official repository unverified MIT (permissive) · 59771617b119cc63 · report
save_cache taeckyung/SoTTA/learner/sotta.py official repository unverified MIT (permissive) · 88a3a9b822c1f39f · report

Tasks

Autonomous DrivingTest-time Adaptation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections