Pith Number

pith:3EU3MUW3

pith:2019:3EU3MUW3Y6TNM3IDTP2I4EKV46

not attested not anchored not stored refs resolved

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

Alexander Kolesnikov, Alexey Dosovitskiy, Andre Susano Pinto, Carlos Riquelme, Joan Puigcerver, Josip Djolonga, Lucas Beyer, Marcin Michalski, Mario Lucic, Maxim Neumann, Michael Tschannen, Neil Houlsby, Olivier Bachem, Olivier Bousquet, Pierre Ruyssen, Sylvain Gelly, Xiaohua Zhai

The Visual Task Adaptation Benchmark defines good representations as those that adapt to diverse unseen tasks with few examples.

arxiv:1910.04867 v2 · 2019-10-01 · cs.CV · cs.LG · 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{3EU3MUW3Y6TNM3IDTP2I4EKV46}

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

We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples.

C2weakest assumption

That performance on the 19 selected tasks under few-shot linear or fine-tuning adaptation is a reliable proxy for representation quality on arbitrary future vision problems.

C3one line summary

VTAB is a 19-task benchmark that measures representation quality by few-shot adaptation performance across diverse vision domains, with a controlled large-scale comparison of popular pretraining methods.

References

25 extracted · 25 resolved · 7 Pith anchors

[1] DeepMind Lab · arXiv:1612.03801

[2] Large scale adversarial representation learning 1907

[3] Scaling and Benchmarking Self-Supervised Visual Representation Learning 1905 · arXiv:1905.01235

[4] Rethinking ImageNet pre-training.arXiv preprint arXiv:1811.08883 · arXiv:1811.08883

[5] J., Razavi, A., Doersch, C., Eslami, S., and Oord, A 1905

Formal links

2 machine-checked theorem links

Cited by

25 papers in Pith

Weierstrass Positional Encoding for Vision Transformers

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

TOAST: Transformer Optimization using Adaptive and Simple Transformations

Sparse Orthogonal Parameters Tuning for Continual Learning

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

Receipt and verification

First computed	2026-05-17T23:38:12.891040Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d929b652dbc7a6d66d039bf48e1155e7bd4d0d8336f66fa3c9da0729f98ec8d3

Aliases

arxiv: 1910.04867 · arxiv_version: 1910.04867v2 · doi: 10.48550/arxiv.1910.04867 · pith_short_12: 3EU3MUW3Y6TN · pith_short_16: 3EU3MUW3Y6TNM3ID · pith_short_8: 3EU3MUW3

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/3EU3MUW3Y6TNM3IDTP2I4EKV46 \
  | 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: d929b652dbc7a6d66d039bf48e1155e7bd4d0d8336f66fa3c9da0729f98ec8d3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2ee84f2872483f7fc0373f486fda0ec03e71cdcf6d2e260eb245a11256983169",
    "cross_cats_sorted": [
      "cs.LG",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2019-10-01T17:06:29Z",
    "title_canon_sha256": "01dfec4774dbcf3571afc230ad20ba5f5e08b81e5bbc3a0773410759e70002cf"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1910.04867",
    "kind": "arxiv",
    "version": 2
  }
}