Pith Number

pith:CZ3DEHME

pith:2020:CZ3DEHME7BS6PIONOW2Q2ODFQF

not attested not anchored not stored refs resolved

Tent: Fully Test-time Adaptation by Entropy Minimization

Bruno Olshausen, Dequan Wang, Evan Shelhamer, Shaoteng Liu, Trevor Darrell

A model adapts to new test data at inference time by minimizing the entropy of its predictions.

arxiv:2006.10726 v3 · 2020-06-18 · cs.LG · cs.CV · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{CZ3DEHME7BS6PIONOW2Q2ODFQF}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. It handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark.

C2weakest assumption

That minimizing the entropy of the model's predictions on unlabeled test batches will improve accuracy on the target distribution without causing collapse to trivial solutions or overfitting to batch-specific noise.

C3one line summary

Test-time entropy minimization adapts models by optimizing for confident predictions, reducing error on corrupted ImageNet-C and enabling source-free domain adaptation.

References

12 extracted · 12 resolved · 3 Pith anchors

[1] Multiscale deep equilibrium models 2006

[2] Autodial: Automatic domain alignment layers 2017

[3] Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour · arXiv:1706.02677

[4] Online domain adaptation of a pre-trained cascade of classiﬁers 2021

[5] InProceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech- nologies (NAACL-HLT), pages 681–691 2006

Formal links

2 machine-checked theorem links

Cited by

31 papers in Pith

Sample-wise Targeted Adversarial Attacks on Test-time Adaptation

EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems

Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery

MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation

Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation

Receipt and verification

First computed	2026-05-17T23:38:48.234330Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1676321d84f865e7a1cd75b50d386581544012943770c5152a8d93b1d90eabc8

Aliases

arxiv: 2006.10726 · arxiv_version: 2006.10726v3 · doi: 10.48550/arxiv.2006.10726 · pith_short_12: CZ3DEHME7BS6 · pith_short_16: CZ3DEHME7BS6PION · pith_short_8: CZ3DEHME

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 1676321d84f865e7a1cd75b50d386581544012943770c5152a8d93b1d90eabc8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0dfe9235fdf41855a1a0adae0ccd98f53b031e0d0df549f0e42487e3353063f2",
    "cross_cats_sorted": [
      "cs.CV",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2020-06-18T17:55:28Z",
    "title_canon_sha256": "633f4b66ea7dd4e96d2d1469359bec004d94ae76ea4beb07a36a18ae6a9896af"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2006.10726",
    "kind": "arxiv",
    "version": 3
  }
}