Pith Number

pith:Z3QZVUI6

pith:2021:Z3QZVUI6UTIZR5M5HYQSJDLIKY

not attested not anchored not stored refs resolved

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

Adrien Bardes, Jean Ponce, Yann LeCun

VICReg prevents collapse to constant embeddings in self-supervised learning by adding an explicit variance term per dimension plus covariance regularization.

arxiv:2105.04906 v3 · 2021-05-11 · cs.CV · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{Z3QZVUI6UTIZR5M5HYQSJDLIKY}

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

VICReg achieves results on par with the state of the art on several downstream tasks. In addition, we show that incorporating our new variance term into other methods helps stabilize the training and leads to performance improvements.

C2weakest assumption

The assumption that enforcing per-dimension variance above a fixed threshold (combined with covariance regularization) is sufficient to eliminate collapse across architectures and datasets without introducing new failure modes or requiring architecture-specific adjustments.

C3one line summary

VICReg prevents collapse in self-supervised image embeddings via explicit variance, invariance, and covariance regularization and matches state-of-the-art downstream performance.

References

119 extracted · 119 resolved · 5 Pith anchors

[1] Self-labelling via simultaneous clustering and representation learning 2020

[2] Learning representations by maximizing mutual information across views 2019

[3] Bautista, Artsiom Sanakoyeu, Ekaterina Sutter, and Björn Ommer 2016

[4] Signature verification using a “siamese” time delay neural network 1994

[5] Deep clustering for unsupervised learning 2018

Formal links

3 machine-checked theorem links

Cited by

30 papers in Pith

Uncovering the Latent Potential of Deep Intermediate Representations

Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture

Understanding Self-Supervised Learning via Latent Distribution Matching

Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds

Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data

Receipt and verification

First computed	2026-05-17T23:38:51.093051Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cee19ad11ea4d198f59d3e21248d685611db12ed366cbcf1f061fe9bdcde2786

Aliases

arxiv: 2105.04906 · arxiv_version: 2105.04906v3 · doi: 10.48550/arxiv.2105.04906 · pith_short_12: Z3QZVUI6UTIZ · pith_short_16: Z3QZVUI6UTIZR5M5 · pith_short_8: Z3QZVUI6

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/Z3QZVUI6UTIZR5M5HYQSJDLIKY \
  | 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: cee19ad11ea4d198f59d3e21248d685611db12ed366cbcf1f061fe9bdcde2786

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "369d5bbba7f095e3dc758d10cbbf40559d032349b243141452acb338d3ae81e9",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2021-05-11T09:53:21Z",
    "title_canon_sha256": "8bc0a69c90c72dd6963df5adfd4d9898ef7492bc826dadfa623cd2f91e796c9a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2105.04906",
    "kind": "arxiv",
    "version": 3
  }
}