Methods › General › Self-Supervised Learning › SimCLR
SimCLR
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SimCLR is a framework for contrastive learning of visual representations. It learns representations by maximizing agreement between differently augmented views of the same data example via a contrastive loss in the latent space. It consists of:
-
A stochastic data augmentation module that transforms any given data example randomly resulting in two correlated views of the same example, denoted x̃ᵢ and x̃ⱼ, which is considered a positive pair. SimCLR sequentially applies three simple augmentations: random cropping followed by resize back to the original size, random color distortions, and random Gaussian blur. The authors find random crop and color distortion is crucial to achieve good performance.
-
A neural network base encoder f(·) that extracts representation vectors from augmented data examples. The framework allows various choices of the network architecture without any constraints. The authors opt for simplicity and adopt ResNet to obtain hᵢ = f(x̃ᵢ) = ResNet(x̃ᵢ) where hᵢ ∈ℝᵈ is the output after the average pooling layer.
-
A small neural network projection head g(·) that maps representations to the space where contrastive loss is applied. Authors use a MLP with one hidden layer to obtain zᵢ = g(hᵢ) = W⁽²⁾σ(W⁽¹⁾hᵢ) where σ is a ReLU nonlinearity. The authors find it beneficial to define the contrastive loss on zᵢ’s rather than hᵢ’s.
-
A contrastive loss function defined for a contrastive prediction task. Given a set {x̃ₖ} including a positive pair of examples x̃ᵢ and x̃ⱼ , the contrastive prediction task aims to identify x̃ⱼ in {x̃ₖ}_(k≠i) for a given x̃ᵢ.
A minibatch of N examples is randomly sampled and the contrastive prediction task is defined on pairs of augmented examples derived from the minibatch, resulting in 2N data points. Negative examples are not sampled explicitly. Instead, given a positive pair, the other 2(N − 1) augmented examples within a minibatch are treated as negative examples. A NT-Xent (the normalized temperature-scaled cross entropy loss) loss function is used (see components).
In Syntology verified reference implementation at level V3; retrieve with get_reference_implementation(name='SimCLR'). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2002.05709) is about this method is not checked.
Origin paper of this answer, arXiv:2002.05709 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified (of 137 harvested samples) · 52 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 240 · with a code link: 127 · where Syntology ran a sample: 38 (33 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (38 of 240 tagged: 33 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 240, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Probabilistic Variational Contrastive Learning 11 Jun 2025 · 0 repositories · arXiv:2506.10159
-
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data 10 Jun 2025 · 1 repository · arXiv:2506.10031
-
Circumventing Backdoor Space via Weight Symmetry 9 Jun 2025 · 1 repository · arXiv:2506.07467
-
SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification 20 May 2025 · 1 repository · arXiv:2505.14561
-
Representation Learning via Non-Contrastive Mutual Information 23 Apr 2025 · 0 repositories · arXiv:2504.16667
-
Impact of Language Guidance: A Reproducibility Study 10 Apr 2025 · 0 repositories · arXiv:2504.08140
-
Unsupervised Detection of Fraudulent Transactions in E-commerce Using Contrastive Learning 24 Mar 2025 · 0 repositories · arXiv:2503.18841
-
A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics 21 Mar 2025 · 0 repositories · arXiv:2503.17538
-
SinSim: Sinkhorn-Regularized SimCLR 13 Feb 2025 · 0 repositories · arXiv:2502.10478
-
Dataset Ownership Verification in Contrastive Pre-trained Models 11 Feb 2025 · 1 repository · arXiv:2502.07276
-
Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling 29 Jan 2025 · 1 repository · arXiv:2501.17772
-
Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant" 21 Dec 2024 · 1 repository · arXiv:2412.16522
-
Self-Supervised Radiograph Anatomical Region Classification -- How Clean Is Your Real-World Data? 20 Dec 2024 · 0 repositories · arXiv:2412.15967
-
Maximising Histopathology Segmentation using Minimal Labels via Self-Supervision 19 Dec 2024 · 0 repositories · arXiv:2412.15389
-
AmCLR: Unified Augmented Learning for Cross-Modal Representations 10 Dec 2024 · 1 repository · arXiv:2412.07979
-
Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement 6 Dec 2024 · 0 repositories · arXiv:2412.04898
-
Tight PAC-Bayesian Risk Certificates for Contrastive Learning 4 Dec 2024 · 1 repository · arXiv:2412.03486
-
Explorations in Self-Supervised Learning: Dataset Composition Testing for Object Classification 1 Dec 2024 · 0 repositories · arXiv:2412.00770
-
Breccia and basalt classification of thin sections of Apollo rocks with deep learning 28 Oct 2024 · 1 repository · arXiv:2410.21024
-
Accelerating Augmentation Invariance Pretraining 27 Oct 2024 · 0 repositories · arXiv:2410.22364
-
Rethinking Positive Pairs in Contrastive Learning 23 Oct 2024 · 0 repositories · arXiv:2410.18200
-
SigCLR: Sigmoid Contrastive Learning of Visual Representations 22 Oct 2024 · 0 repositories · arXiv:2410.17427
-
Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods 5 Oct 2024 · 0 repositories · arXiv:2410.04289
-
BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel Optimization 3 Oct 2024 · 0 repositories · arXiv:2410.02387
-
Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks 27 Sep 2024 · 0 repositories · arXiv:2409.18685
-
Self-supervised Pretraining for Cardiovascular Magnetic Resonance Cine Segmentation 26 Sep 2024 · 1 repository · arXiv:2409.18100
-
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition 23 Sep 2024 · 1 repository
-
Contrastive Learning for Character Detection in Ancient Greek Papyri 16 Sep 2024 · 0 repositories · arXiv:2409.10156
-
Label-free Monitoring of Self-Supervised Learning Progress 10 Sep 2024 · 0 repositories · arXiv:2409.06612
-
Learning Tree-Structured Composition of Data Augmentation 26 Aug 2024 · 1 repository · arXiv:2408.14381
-
Improving Nonlinear Projection Heads using Pretrained Autoencoder Embeddings 25 Aug 2024 · 1 repository · arXiv:2408.14514
-
CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture 14 Aug 2024 · 1 repository · arXiv:2408.07514
-
MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations 18 Jun 2024 · 1 repository · arXiv:2406.12368
-
Scale-Translation Equivariant Network for Oceanic Internal Solitary Wave Localization 18 Jun 2024 · 1 repository · arXiv:2406.13060
-
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks 10 Jun 2024 · 0 repositories · arXiv:2406.06079
-
Alignment Calibration: Machine Unlearning for Contrastive Learning under Auditing 5 Jun 2024 · 0 repositories · arXiv:2406.03603
-
Maximum Manifold Capacity Representations in State Representation Learning 22 May 2024 · 0 repositories · arXiv:2405.13848
-
A Mutual Information Perspective on Federated Contrastive Learning 3 May 2024 · 0 repositories · arXiv:2405.02081
-
Self-supervised learning for classifying paranasal anomalies in the maxillary sinus 29 Apr 2024 · 1 repository · arXiv:2404.18599
-
Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations 23 Apr 2024 · 1 repository · arXiv:2404.14913
-
Comparing Self-Supervised Learning Techniques for Wearable Human Activity Recognition 8 Apr 2024 · 1 repository · arXiv:2404.15331
-
Self-Supervised Backbone Framework for Diverse Agricultural Vision Tasks 22 Mar 2024 · 0 repositories · arXiv:2403.15248
-
Do Generated Data Always Help Contrastive Learning? 19 Mar 2024 · 1 repository · arXiv:2403.12448Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
Car Damage Detection and Patch-to-Patch Self-supervised Image Alignment 11 Mar 2024 · 1 repository · arXiv:2403.06674Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
Poly-View Contrastive Learning 8 Mar 2024 · 0 repositories · arXiv:2403.05490
-
Self-Supervised Multiple Instance Learning for Acute Myeloid Leukemia Classification 8 Mar 2024 · 0 repositories · arXiv:2403.05379
-
Multimodal Transformer for Comics Text-Cloze 6 Mar 2024 · 0 repositories · arXiv:2403.03719
-
Self-supervised Visualisation of Medical Image Datasets 22 Feb 2024 · 1 repository · arXiv:2402.14566
-
The Common Stability Mechanism behind most Self-Supervised Learning Approaches 22 Feb 2024 · 1 repository · arXiv:2402.14957
-
Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning 19 Feb 2024 · 1 repository · arXiv:2402.11816
-
CochCeps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear Cepstrum-based Masking for Speech Emotion Recognition 10 Feb 2024 · 0 repositories · arXiv:2402.06923
-
A Probabilistic Model Behind Self-Supervised Learning 2 Feb 2024 · 1 repository · arXiv:2402.01399Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
Optimizing contrastive learning for cortical folding pattern detection 31 Jan 2024 · 1 repository · arXiv:2401.18035
-
Detecting and recognizing characters in Greek papyri with YOLOv8, DeiT and SimCLR 23 Jan 2024 · 0 repositories · arXiv:2401.12513
-
Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing 11 Jan 2024 · 0 repositories · arXiv:2401.05730
-
Automated Detection of Myopic Maculopathy in MMAC 2023: Achievements in Classification, Segmentation, and Spherical Equivalent Prediction 8 Jan 2024 · 1 repository · arXiv:2401.03615
-
GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning 3 Jan 2024 · 1 repository · arXiv:2401.01990
-
Time-Series Contrastive Learning against False Negatives and Class Imbalance 19 Dec 2023 · 0 repositories · arXiv:2312.11939
-
SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer 2 Dec 2023 · 0 repositories · arXiv:2312.01187
-
Contrastive Left-Right Wearable Sensors (IMUs) Consistency Matching for HAR 21 Nov 2023 · 0 repositories · arXiv:2311.12674
-
Lesion Search with Self-supervised Learning 18 Nov 2023 · 0 repositories · arXiv:2311.11014
-
SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling 23 Oct 2023 · 0 repositories · arXiv:2310.14736
-
ARNIQA: Learning Distortion Manifold for Image Quality Assessment 20 Oct 2023 · 1 repository · arXiv:2310.14918Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
An Empirical Study of Self-supervised Learning with Wasserstein Distance 16 Oct 2023 · 0 repositories · arXiv:2310.10143
-
Adaptive Multi-head Contrastive Learning 9 Oct 2023 · 1 repository · arXiv:2310.05615
-
URLOST: Unsupervised Representation Learning without Stationarity or Topology 6 Oct 2023 · 0 repositories · arXiv:2310.04496
-
Beyond Random Augmentations: Pretraining with Hard Views 5 Oct 2023 · 2 repositories · arXiv:2310.03940
-
ScaleNet: An Unsupervised Representation Learning Method for Limited Information 3 Oct 2023 · 0 repositories · arXiv:2310.02386
-
Contrastive Speaker Embedding With Sequential Disentanglement 23 Sep 2023 · 0 repositories · arXiv:2309.13253
-
FLSL: Feature-level Self-supervised Learning 21 Sep 2023 · 1 repository
-
Identifiable Contrastive Learning with Automatic Feature Importance Discovery 21 Sep 2023 · 1 repository
-
Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals 11 Sep 2023 · 0 repositories · arXiv:2309.05843
-
Adapting Self-Supervised Representations to Multi-Domain Setups 7 Sep 2023 · 0 repositories · arXiv:2309.03999
-
Dynamically Scaled Temperature in Self-Supervised Contrastive Learning 2 Aug 2023 · 1 repository · arXiv:2308.01140
-
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity 31 Jul 2023 · 0 repositories · arXiv:2308.00177
-
VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localization 31 Jul 2023 · 1 repository · arXiv:2308.00090
-
Geometry-Aware Adaptation for Pretrained Models 23 Jul 2023 · 0 repositories · arXiv:2307.12226
-
Hallucination Improves the Performance of Unsupervised Visual Representation Learning 22 Jul 2023 · 0 repositories · arXiv:2307.12168
-
Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series 20 Jul 2023 · 0 repositories · arXiv:2307.10923
-
Systematic comparison of semi-supervised and self-supervised learning for medical image classification 18 Jul 2023 · 1 repository · arXiv:2307.08919
-
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition 15 Jul 2023 · 2 repositories · arXiv:2307.07791
-
Substance or Style: What Does Your Image Embedding Know? 10 Jul 2023 · 0 repositories · arXiv:2307.05610
-
DUET: 2D Structured and Approximately Equivariant Representations 28 Jun 2023 · 1 repository · arXiv:2306.16058Syntology official (archive's flag): 9 ran · 9 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 15 pointer-only (licence)
-
Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination methods 28 Jun 2023 · 0 repositories · arXiv:2306.16122
-
ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Function 7 Jun 2023 · 0 repositories · arXiv:2306.04175
-
BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs 6 Jun 2023 · 1 repository · arXiv:2306.03355
-
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners 1 Jun 2023 · 2 repositories · arXiv:2306.00984Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Augmentation-aware Self-supervised Learning with Conditioned Projector 31 May 2023 · 1 repository · arXiv:2306.06082Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified (of 9 harvested samples) · 9 pointer-only (licence)
-
Morphological Classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs 31 May 2023 · 0 repositories · arXiv:2306.00031
-
MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations 29 May 2023 · 1 repository · arXiv:2305.17191
-
Matrix Information Theory for Self-Supervised Learning 27 May 2023 · 3 repositories · arXiv:2305.17326Syntology official (archive's flag): 3 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization 19 May 2023 · 1 repository · arXiv:2305.11965
-
Tuned Contrastive Learning 18 May 2023 · 0 repositories · arXiv:2305.10675
-
State Representation Learning Using an Unbalanced Atlas 17 May 2023 · 1 repository · arXiv:2305.10267
-
Learning Better Contrastive View from Radiologist's Gaze 15 May 2023 · 1 repository · arXiv:2305.08826
-
Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations 25 Apr 2023 · 0 repositories · arXiv:2304.13089
-
Explaining, Analyzing, and Probing Representations of Self-Supervised Learning Models for Sensor-based Human Activity Recognition 14 Apr 2023 · 0 repositories · arXiv:2304.07304
-
Enhancing Self-Supervised Learning for Remote Sensing with Elevation Data: A Case Study with Scarce And High Level Semantic Labels 13 Apr 2023 · 1 repository · arXiv:2304.06857
-
Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies 2 Apr 2023 · 0 repositories · arXiv:2304.00601
-
Large-scale pretraining on pathological images for fine-tuning of small pathological benchmarks 28 Mar 2023 · 1 repository · arXiv:2303.15693
Tasks archive 2025-07-28
20 shown of 202 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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