SOTAVerified

Contrastive Learning

Contrastive Learning is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.

It has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.

(Image credit: Schroff et al. 2015)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 6251–6300 of 6661 papers

TitleStatusHype
Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine LearningCode0
Partially View-aligned Representation Learning with Noise-robust Contrastive LossCode1
Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive LearningCode1
Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning—0
Using contrastive learning to improve the performance of steganalysis schemes—0
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningCode1
Consistent Assignment for Representation Learning—0
A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives—0
Towards Robust Graph Contrastive Learning—0
Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning—0
MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation—0
Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning ViewCode1
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningCode1
Molecular Contrastive Learning of Representations via Graph Neural NetworksCode1
CUPR: Contrastive Unsupervised Learning for Person Re-identification—0
Contrastive Learning Inverts the Data Generating ProcessCode1
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution CalibrationCode1
Dissecting Supervised Contrastive LearningCode0
COCO-LM: Correcting and Contrasting Text Sequences for Language Model PretrainingCode1
Self-Supervised Multisensor Change Detection—0
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-TuningCode1
Large-Scale Representation Learning on Graphs via BootstrappingCode1
Semantically-Conditioned Negative Samples for Efficient Contrastive Learning—0
CDPAM: Contrastive learning for perceptual audio similarityCode1
Negative Data AugmentationCode1
DetCo: Unsupervised Contrastive Learning for Object DetectionCode1
Contrastive Embeddings for Neural ArchitecturesCode1
Quantifying and Mitigating Privacy Risks of Contrastive LearningCode1
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive LearningCode0
Semi-Supervised Action Recognition with Temporal Contrastive LearningCode1
Nonlinear Independent Component Analysis for Discrete-Time and Continuous-Time SignalsCode0
Cleora: A Simple, Strong and Scalable Graph Embedding SchemeCode1
A Computational Framework for Slang GenerationCode0
"Is depression related to cannabis?": A knowledge-infused model for Entity and Relation Extraction with Limited Supervision—0
NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose EstimationCode1
Calibrating and Improving Graph Contrastive LearningCode0
Supervised Momentum Contrastive Learning for Few-Shot Classification—0
Unified Framework for Feature Extraction based on Contrastive Learning—0
Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive LearningCode1
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude LearningCode1
TCLR: Temporal Contrastive Learning for Video RepresentationCode1
Few-shot Action Recognition with Prototype-centered Attentive LearningCode1
Scaling Deep Contrastive Learning Batch Size under Memory Limited SetupCode1
SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning—0
Label Contrastive Coding based Graph Neural Network for Graph ClassificationCode1
Learning to Anticipate Egocentric Actions by Imagination—0
Big Self-Supervised Models Advance Medical Image ClassificationCode1
Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification—0
Pneumonia Detection on Chest X-ray using Radiomic Features and Contrastive Learning—0
Explicit homography estimation improves contrastive self-supervised learning—0
Show:102550
← PrevPage 126 of 134Next →
All datasetsimagenet-1k10,000 People - Human Pose Recognition DataCIFAR-10STL-10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6—Unverified
2ResNet50ImageNet Top-1 Accuracy73—Unverified
3ResNet50ImageNet Top-1 Accuracy71.1—Unverified
4ResNet50ImageNet Top-1 Accuracy69.3—Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6—Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8—Unverified
7ResNet50ImageNet Top-1 Accuracy63.6—Unverified
8ResNet50ImageNet Top-1 Accuracy61.5—Unverified
9ResNet50ImageNet Top-1 Accuracy61.5—Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3—Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55—Unverified